Training a Custom Image Classifier with Tensorflow, Converting to ONNX and using it in OpenCV DNN module

Training a Custom Image Classifier with Tensorflow, Converting to ONNX and using it in OpenCV DNN module

In the previous tutorial we learned how the DNN module in OpenCV works, we went into a lot of details regarding different aspects of the module including where to get the models, how to configure them, etc. 

This Tutorial will build on top of the previous one so if you haven’t read the previous post then you can read that here. 

Today’s post is the second tutorial in our brand new 3 part Deep Learning with OpenCV series. All three posts are titled as:

  1. Deep Learning with OpenCV DNN Module, A Comprehensive Guide
  2. Training a Custom Image Classifier with OpenCV, Converting to ONNX, and using it in OpenCV DNN module.
  3. Using a Custom Trained Object Detector with OpenCV DNN Module.

In this post, we will train a custom image classifier with Tensorflow’s Keras API. So if you want to learn how to get started creating a Convolutional Neural Network using Tensorflow, then this post is for you, and not only that but afterward, we will also convert our trained .h5 model to ONNX format and then use it with OpenCV DNN module.

Converting your model to onnx will give you more than 3x reduction in model size.

This whole process shows you how to train models in Tensorflow and then deploy it directly in OpenCV.

What’s the advantage of using the trained model in OpenCV vs using it in Tensorflow ?

So here are some points you may want to consider.

  • By using OpenCV’s DNN module, the final code is a lot compact and simpler.
  • Someone who’s not familiar with the training framework like TensorFlow can also use this model.
  • There are cases where using OpenCV’s DNN module will give you faster inference results for the CPU. See these results in LearnOpenCV by Satya.
  • Besides supporting CUDA based NVIDIA’s GPU, OpenCV’s DNN module also supports OpenCL based Intel GPUs.
  • Most Importantly by getting rid of the training framework (Tensorflow) not only makes the code simpler but it ultimately gets rid of a whole framework, this means you don’t have to build your final application with a heavy framework like TensorFlow. This is a huge advantage when you’re trying to deploy on a resource-constrained edge device, e.g. a Raspberry pie

So this way you’re getting the best of both worlds, a framework like Tensorflow for training and OpenCV DNN for faster inference during deployment.

This tutorial can be split into 3 parts.

  1. Training a Custom Image Classifier in OpenCV with Tensorflow
  2. Converting Our Classifier to ONNX format.
  3. Using the ONNX model directly in the OpenCV DNN module.

Let’s start with the Code

Download Code for this post

Download Code for this post

Part 1: Training a Custom Image Classifier with Tensorflow:

For this tutorial you need OpenCV and Tensorflow 2.2

So you should do:

pip install opencv-contrib-python==
Or install from Source, Make sure to change the version)

pip install tensorflow
(Or install tensorflow-gpu from source)

Note: The reason I’m asking you to install version 4.0 instead of the latest 4.3 version of OpenCV is because later on we’ll be using a function called readNetFromONNX() now with our model this function was giving an error in 4.3 and 4.2, possibly due to some bug in those versions. This does not mean that you can’t use custom models with those versions but that for my specific case there was an issue. Converting models only takes 2-3 lines of code but sometimes you get ambiguous errors which are hard to diagnose, but it can be done.

Hopefully, the conversion process will get better in the future.

One thing you can do is create a custom environment (with Anaconda or virtualenv) in which you can install version 4.0 without affecting your root environment and if you’re using google colab for this tutorial then you don’t need to worry about that.

You can go ahead and download the source code from the download code section. After downloading the zip folder, unzip it and you will have the following directory structure.

You can start by importing the libraries:

Let’s see how you would go about training a basic Convolutional Network in Tensorflow. I assume you know some basics of deep learning. Also in this tutorial, I will be teaching how to construct and train a classifier using a real-world dataset, not a toy one, I will not go in-depth and explain the theory behind neural networks. If you want to start learning deep learning then you can take a look at Andrew Ng’s Deep Learning specialization, although this specialization is basic and covers mostly foundational things now if your end goal is to specialize in computer Vision then I would strongly recommend that you first learn Image Processing and Classical Computer Vision techniques from my 3 month comprehensive course here.

The Dataset we’re going to use here is a dataset of 5 different flowers, namely rose, tulips, sunflower, daisy and dandelion. I avoided the usual cats and dogs dataset.

You can download the dataset from a url, you just have to run this cell

After downloading the dataset you’ll have to unzip it, you can also do this manually.

After extracting you can check the folder named flower_photos in your current directory which will contain these 5 subfolders.

You can check the number of images in each class using the code below.

Found 699 images of sunflowers
Found 898 images of dandelion
Found 633 images of daisy
Found 799 images of tulips
Found 641 images of roses
[‘daisy’, ‘dandelion’, ‘roses’, ‘sunflowers’, ‘tulips’]

Generate Images:

Now it’s time to load up the data, now since the data is approx 218 MB, we can actually load it in RAM but most real datasets are large several GBs in size, and will fit in your RAM. In those scenarios, you use data generators to fetch batches of data and feed it to the neural network during training, so today we’ll also be using a data generator to load the data.

Before we can pass the images to a deep learning model, we need to do some preprocessing, like resize the image in the required shape, convert them to floating-point tensors, rescale the pixel values from 0-255 to 0-1 range as this helps in training.

Fortunately, all of this can be done by the ImageDataGenerator class in tf.keras. Not only that but the ImageDataGenerator Class can also perform data augmentation. Data augmentation means that the generator takes your image and performs random transformations like randomly rotating, zooming, translating, and performing other such operations to the image. This is really effective when you don’t have much data as this increases your dataset size on the fly and your dataset contains more variation which helps in generalization.

As you’ve already seen that each flower class has less than 1000 examples, so in our case data augmentation will help a lot. It will expand our dataset.

When training a Neural Network, we normally use 2 datasets, a training dataset and a validation dataset. The neural network tunes its parameters using the training dataset and the validation dataset is used for the evaluation of the Network’s performance.

Found 2939 images belonging to 5 classes.
Found 731 images belonging to 5 classes.

Note: Usually when using an ImageDataGenerator to read from a directory with data augmentation we usually have two folders for each class because data augmentation is done only to the training dataset, not the validation set as this set is only used for evaluation. So I’ve actually created two data generators instances for the same directory with a validation split of 20% and used a constant random seed on both generators so there is no data overlap.

I’ve rarely seen people split with augmentation this way but this approach actually works and saves us the time of splitting data between two directories.

Visualize Images:

It’s always a good idea to see what images look like in your dataset, so here’s a function that will plot new images from the dataset each time you run it.

Alright, now we’ll use the above function to first display few of the original images using the validation generator.

Now we will generate some Augmented images using the train generator. Notice how images are rotated, zoomed etc.

Create the Model

Since we’re using Tensorflow 2 (TF2) and in TF2 the most popular way to go about creating neural networks is by using the Keras API. Previously Keras used to be a separate framework (it still is) but not so long ago because of Keras’ popularity in the community it was included in TensorFlow as the default high-level API. This abstraction allows developers to use TensorFlow’s low-level functionality with high-level Keras code. 

This way you can design powerful neural networks in just a few lines of code. E.g. take a look at how we have created an effective Convolutional Networks.

A typical neural network has a bunch of layers, in a Convolutional network, you’ll see convolutional layers. These layers are created with the Conv2d function. Take a look at the first layer:

      Conv2D(16, 3, padding=’same’, activation=’relu’, input_shape =(IMG_HEIGHT, IMG_WIDTH ,3))

The number 16 refers to the number of filters in that layer, normally we increase the number of filters as you add more layers. You should notice that I double the number of filters in each subsequent convolutional layer i.e. 16, 32, 64 … , this is common practice. In the first layer, you also specify a fix input shape that the model will accept, which we have already set as 200x200

Another thing you’ll see is that typically a convolutional layer is followed by a pooling layer. So the Conv layer outputs a number of feature maps and the pooling layer reduces the spatial size (width and height) of these feature maps which effectively reduces the number of parameters in the network thus reducing computation.

So you’ll commonly a convolutional layer followed by a pooling layer, this is normally repeated several times, at each stage the size is reduced and the no of filters is increased. We are using a MaxPooling layer there are other pooling types too e.g. AveragePooling.

The Dropout layer randomly drops x% percentage of parameters from the network, this allows the network to learn robust features. In the network above I’m using dropout twice and so in those stages I’m dropping 10% of the parameters. The whole purpose of the Dropout layer is to reduce overfitting.

Now before we add the final layer we need to flatten the output in a single-dimensional vector, this can be done by the flatten layer but a better method is using the  GlobalAveragePooling2D Layer, which flattens the output while reducing the parameters.

Finally, before our last layer, we also use a Dense layer (A fully connected layer) with 1024 units. The final layer contains the number of units equal to the number of classes. The activation function here is softmax as I want the network to produce class probabilities at the end.

Compile the model

Before we can start training the network we need to compile it, this is the step where we define our loss function, optimizer, and metrics.

For this example, we are using the ADAM optimizer and a categorical cross-entropy loss function as we’re dealing with a multi-class classification problem. The only metric we care about right now is the accuracy of the model.

Model summary

By using the built-in method called summary() we can see the whole architecture of the model that we just created. You can see the total parameter count and the number of params in each layer.

Notice how the number of params are 0 in all layers except the Conv and Dense layers, this is because these are the only two types of layers here which are actually involved in learning.

Training the Model:

You can start training the model using the method but first specify the number of epochs, and the steps per epoch. 

Epoch: A single epoch means 1 pass of the whole data meaning an epoch is considered done when the model goes over all the images in the training data and uses it for gradient calculation and optimizations. So this number decides how many times the model will go over your whole data.

Steps per epoch: A single step means the model goes over a single batch of the data, so steps per epoch tells, after how many steps should an epoch be considered done. This should be set to dataset_size / batch_size which is the number of steps required to go over the whole data once.

Let’s train our model for 60 epochs.


You can see in the last epoch that our validation loss is low and accuracy is high so our model has successfully converged, we can further verify this by plotting the loss and accuracy graphs.

After you’re done training it’s a good practice to plot accuracy and loss graphs.

The model has slightly overfitted at the end but that is okay considering the number of images we used and our model’s capacity.

You can test out the trained model on a single test image using this code. Make sure to carry out the same preprocessing steps you used before training for e.g. since we trained on normalized images in range 0-1, we will need to divide any new image with 255 before passing it to the model for prediction.

Predicted Flowers is : roses, 85.61%

Notice that we are converting our model from BGR to RGB color format. This is because TensorFlow has trained the model using images in RGB format whereas OpenCV reads images in BGR format, so we have to reverse channels before we can perform prediction.

Finally when you’re satisfied with the model you save it in .h5 format using function.

Part 2: Converting Our Classifier to ONNX format

Now that we have trained our model, it’s time to convert it to ONNX format.

What is ONNX ?

ONNX stands for Open neural network exchange. ONNX is an industry-standard format for changing model frameworks, this means you can train a model in PyTorch or any other common frameworks and then convert to onnx and then convert back to TensorFlow or any other framework. 

So ONNX allows developers to move models between different frameworks such as CNTK, Caffe2, Tensorflow, PyTorch etc.

So why are we converting to ONNX ?

Remember our goal is to use the above custom trained model in DNN module but the issue is the DNN module does not support using the .h5 Keras model directly. So we have to convert our .h5 model to a .onnx model after doing this we will be able to take the onnx model and plug it into the DNN module.

Note: Even if you saved the model in saved_model format then you still can’t use it directly 

You need to use keras2onnx module to perform the conversion so you should  go ahead and install keras2onnx module.

pip install keras2onnx

You also need to install onnx so that you can save .onnx models to disk.

pip install onnx

After installing keras2onnx, you can use its convert_keras function to convert the model, we will also serialize the model to disk using keras2onnx.save_model  so we can use it later.

tf executing eager_mode: True
tf.keras model eager_mode: False
The ONNX operator number change on the optimization: 57 -> 25

Now we’re ready to use this model in the DNN module. Check how your ~7.5 MB .h5 model now has reduced to ~2.5 MB .onnx model, a 3x reduction in size. Make sure to check out  keras2onnx repo for more details.

Note: You can even use this model with just ONNX using onnxruntime module which itself is pretty powerful considering the support of multiple hardware accelerations.

Using the ONNX model in the OpenCV DNN module:

Now we will take this ONNX model and use it directly in our DNN module.

Let’s use this as a test image.

Here’s the code to test the ONNX model on the image.

Here’s the result of a few images which I took from google, I’m using my custom function classify_flower() to classify these images. You can find this function’s code inside the downloaded Notebook.

If you want to learn about doing image classification using the DNN module in detail then make to read the previous post,  Deep learning with OpenCV DNN module. Where I have explained each step in detail.

What’s Next?

computer vision

If you want to go forward from here and learn more advanced things and go into more detail, understand theory and code of different algorithms then be sure to check out our Computer Vision & Image Processing with Python Course (Urdu/Hindi). In this course, I go into a lot of detail regarding vision fundamentals and cover a plethora of algorithms and techniques to help you master Computer Vision.

The 3 month course contains:

✔ 125 Video Lectures
✔ Discussion Forums
✔ Quizzes
✔ 100+ High Quality Jupyter notebooks
✔ Practice Assignments
✔Certificate of Completion

If you want to start a career in Computer Vision & Artificial Intelligence then this course is for you. One of the best things about this course is that the video lectures are in Urdu/Hindi Language without any compromise on quality, so there is a personal/local touch to it.


In today’s post we first learned how to train an image classifier with tf.keras, after that we learned how to convert our trained .h5 model to .onnx model.

Finally we learned to use this onnx model using OpenCV’s DNN module.

Although the model we converted today was quite basic but this same pipeline can be used for converting complex models too.

A word of Caution: I personally have faced some issues while converting some types of models so the whole process is not foolproof yet but it’s still pretty good. Make sure to look at keras2onnx repo and this excellent repo of ONNX conversion tutorials.

Deep Learning with OpenCV DNN Module, A Comprehensive Guide

Deep Learning with OpenCV DNN Module, A Comprehensive Guide

In this tutorial we will go over OpenCV’s DNN module in detail, I plan to cover various important details of the DNN module that is never discussed, things that usually trip of people like, selecting preprocessing params correctly and designing pre and postprocessing pipelines for different models.

This post is the first of 3 in our brand new Deep Learning with OpenCV series. All three posts are titled as:

  1. Deep Learning with OpenCV DNN Module, A Comprehensive Guide
  2. Training a Custom Image Classifier with Tensorflow, Converting to ONNX and using it in OpenCV DNN module
  3. Using a Custom Trained Object Detector with OpenCV DNN Module

This post can be split into 3 sections.

  1. Introduction to OpenCV’s DNN module.
  2. Using a Caffe DenseNet121 model for classification.
  3. Important Details regarding the DNN module, e.g. where to get models, how to configure them, etc.

If you’re just interested in the image classification part then you can skip to the second section or you can even read this great classification with DNN module post by Adrian. However, if you’re interested in getting to know the DNN module in all its glory then keep reading.

Introduction to OpenCV’s DNN module

First let me start by introducing the DNN module for all those people who are new to it, so as you can probably guess, the DNN module stands for Deep Neural Network module. This is the module in OpenCV which is responsible for all things deep learning related.

It was introduced in OpenCV version 3 and now in version 4.3 it has evolved a lot. This module lets you use pre trained neural networks from popular frameworks like tensorflow, pytorch  etc and use those models directly in OpenCV.

This means you can train models using a popular framework like Tensorflow and then do inference/prediction with just OpenCV.

So what are the benefits here?

Here are some advantages you might want to consider when using OpenCV for inference.

  • By using OpenCV’s DNN module for inference the final code is a lot compact and simpler.
  • Someone who’s not familiar with the training framework can also use the model.
  • Beside supporting CUDA based NVIDIA’s GPU, OpenCV’s DNN module also supports OpenCL based Intel GPUs.
  • Most Importantly by getting rid of the training framework not only makes the code simpler but it ultimately gets rid of a whole framework, this means you don’t have to build your final application with a heavy framework like TensorFlow. This is a huge advantage when you’re trying to deploy on a resource-constrained edge device, e.g. a Raspberry pie.

One thing that might put you off is the fact that OpenCV can’t be used for training deep learning networks. This might sound like a bummer but fret not, for training neural networks you shouldn’t use OpenCV there are other specialized libraries like Tensorflow, PyTorch etc for that task.

So which frameworks can you use to train Neural Networks:

These are the frameworks that are currently supported with the DNN module.

Now there are many interesting pre-trained models already available in the OpenCV Model Zoo that you can use, to keep things simple for this tutorial, I will be using an image classification network to do classification.

I have also made a tutorial on doing Super-Resolution with DNN module and Facial expression recognition that you can look at after going through this post.

Details regarding other types of models are discussed in the 3rd section. By the way, I actually go over 13-14 different types of models in our Computer Vision and Image processing Course. These contain notebooks tutorials and video walk-throughs.

Image Classification pipeline with OpenCV DNN

Now we will be using a DenseNet121 model, which is a caffe model trained on 1000 classes of ImageNet. The model is from the paper Densely Connected Convolutional Networks by Gap Huang et al.

Generally there are 4 steps you need to perform when doing deep learning with DNN module.

  1. Read the image and the target classes.
  2. Initialize the DNN module with an architecture and model parameters.
  3. Perform the forward pass on the image with the module
  4. Post-process the results.

The pre and post processing steps are different for different tasks.

Let’s start with the code

Download Code for this post

Download Code for this post

You can go ahead and download the source code from the download code section. After downloading the zip folder, unzip it and you will have the following directory structure.

Now run the Image Classification with DenseNet121.ipynb notebook, and start executing the cells.

Import Libraries

First we will import the required libraries.

Loading Class Labels

Now we’ll start by loading class names, In this notebook, we are going to classify among 1000 classes defined in ImageNet.

All these classes are in the text file named synset_words.txt. In this text file, each class is in on a new line with its unique id, Also each class has multiple labels for e.g look at the first 3 lines in the text file:

  • ‘n01440764 tench, Tinca tinca’
  • ‘n01443537 goldfish, Carassius auratus’
  • ‘n01484850 great white shark, white shark

So for each line, we have the Class ID, then there are multiple class names, they all are valid names for that class and we’ll just use the first one. So in order to do that we’ll have to extract the second word from each line and create a new list, this will be our labels list.

Number of Classes 1000 [‘n01440764 tench, Tinca tinca’, ‘n01443537 goldfish, Carassius auratus’, ‘n01484850 great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias’, ‘n01491361 tiger shark, Galeocerdo cuvieri’, ‘n01494475 hammerhead, hammerhead shark’]

Extract the Label

Here we will extract the labels (2nd element from each line) and create a labels list.

[‘tench’, ‘goldfish’, ‘great white shark’, ‘tiger shark’, ‘hammerhead’, ‘electric ray’, ‘stingray’, ‘cock’, ‘hen’, ‘ostrich’, ‘brambling’, ‘goldfinch’, ‘house finch’, ‘junco’, ‘indigo bunting’, ‘robin’, ‘bulbul’, ‘jay’, ‘magpie’, ‘chickadee’]

Initializing the DNN Module

Now before we can use the DNN Module we must initialize it using one of the following functions.

  • Caffe Modles: cv2.dnn.readNetFromCaffe
  • Tensorflow Models: cv2.dnn.readNetFromTensorFlow
  • Pytorch Models: cv2.dnn.readNetFromTorch

As you can see the function you use depends upon Original Architecture the model was trained on.

Since we’ll be using a DenseNet121 which was trained using Caffe so our function will be:

retval = cv2.dnn.readNetFromCaffe( prototxt[, caffeModel] )


  • prototxt: Path to the .prototxt file, this is the text description of the architecture of the model.
  • caffeModel: path to the .caffemodel file, this is your actual trained neural network model, it contains all the weights/parameters of the model. This is usually several MBs in size.

Note: If you load the model and proto file via readNetFromTensorFlow then the order of architecture and model inputs are reversed.

Read An Image

Let’s read an example image and display it with matplotlib imshow

Pre-processing the image

Now before you pass an image in the network you need to preprocess it, this means resizing the image to the size it was trained on, for many networks, this is 224×224, in pre-processing step you also do other things like Normalize the image (make the range of intensity values between 0-1) and mean subtraction, etc. These are all the steps the authors did on the images that were used during model training.

Fortunately, In OpenCV you have a function called cv2.dnn.blobFromImage() which most of the time takes care of all the pre-processing for you.

blob = cv2.dnn.blobFromImage(image[, scalefactor[, size[, mean[, swapRB[, crop]]]]])


  • Image Input image.
  • Scalefactor Used to normalize the image. This value is multiplied by the image, value of 1 means no scaling is done.
  • Size The size to which the image will be resized to, this depends upon the each model.
  • Mean These are mean R,G,B Channel values from the whole dataset and these are subtracted from the image’s R,G,B respectively, this gives illumination invariance to the model.
  • swapRB Boolean flag (false by default) this indicates weather swap first and last channels in 3-channel image is necessary.
  • crop flag which indicates whether the image will be cropped after resize or not. If crop is true, input image is resized so one side after resize is equal to the corresponding dimension in size and another one is equal or larger. Then, a crop from the center is performed. If crop is false, direct resize without cropping and preserving aspect ratio is performed.

So After this function we get a 4d blob, this is what we’ll pass to the network.

(1, 3, 224, 224)

Note: There is also blobFromImages() which does the same thing but with multiple images.

Input the Blob Image to the Network 

Here you’re setting up the blob image as the input to the network.

Forward Pass 

Here the actual computation will take place, Most of the time in your whole pipeline will be taken here. Here your image will go through all the model parameters and in the end, you will get the output of the classifier.

Wall time: 166 ms

Total Number of Predictions are: 1000

array([[[-2.0572357 ]], [[-0.18754716]], [[-3.314731 ]], [[-6.196114 ]]], dtype=float32)

Apply Softmax Function to get Probabilities

By looking at the output, you can tell that the model has returned a set of scores for each class but we need Probabilities between 0-1 for each class. We can get them by applying a softmax function on the scores.

array([5.7877337e-06, 3.7540856e-05, 1.6458317e-06, 9.2260699e-08], dtype=float32)

The Maximum probability is the confidence of our target class.


The index Containing the maximum confidence/probability is the index of our target class.


By putting the index from above into our labels list we can get the name of our target class.


As we have successfully performed the classification, now we will just annotate the image with the information we have.

Creating Functions 

Now that we have understood step by step how to create the pipeline for classification using OpenCV’s DNN module, we’ll now create functions that do all the above in a single step. In short we will be creating following two functions.

Initialization Function: This function will contain parts of the network that will be set once, like loading the model.

Main Function: This function will contain all the rest of the code from preprocessing to postprocessing, it will also have the option to either return the image or display it with matplotlib.

Initialization Function

This method will be run once and it will initialize the network with the required files.

Main Method

returndata is set to True when we want to perform classification on video.

Initialize the Classifier

Calling our initializer to initialize the network.

Using our Classifier Function

Now we can call our classifier function and test on multiple images.

Real time Image Classification

If you want to this classifier in real time then here is the code for that.

Important Details Regarding the DNN module 

Let’s discuss some interesting details and some tips to fully utilize the DNN module.

Where to get the pre-trained Models:

Earlier I mentioned that you can get other pre-trained models, so where are they? 

The best place to get pre-trained models is here. This page is a wiki for Deep learning with OpenCV, you will find models that have been tested by the OpenCV team.

There are a variety of models present here, for things like Classification, Pose Detection, Colorization, Segmentation, Face recognition, text detection, style transfer, and more. You can take models from any of the above 5 frameworks.

Just click on the models to go to their repo and download them from there. Note: The models listed on the page above are only the tested models, in theory, you can almost take any pre-trained model and use it in OpenCV. 

A faster and easier way to download models is to go here. Now, this is a python script that will let you download not only the most commonly used models but also some State of the Art ones like Yolo v4 etc. You can download this script and then run from the command line. Alternatively, if you’re in a rush and just one specific model then you can take the downloadable URL of any model and download it.

After downloading the model, you will need a couple of more things before you can actually use the model in the OpenCV dnn module.

You’re now probably familiar with those things, so yeah you will need the model configuration file like the prototxt file we just used with our Caffe model above. You will also need class labels, now for classification problems, models are usually trained on the ImageNet dataset so we needed synset_word.txt file, for Object detection you will find models trained on COCO or Pascal VOC dataset. And similarly, other tasks may require other files.

So where are all these files present ?

You will find most of these configuration files present here and the class names here. If the configuration file you’re looking for is not present in the above links then I would recommend that you look at the GitHub repo of the model, the files would be present there. Otherwise, you have to create it yourself. (More on this later)

After getting the configuration files, the only thing you need is the pre-processing parameters that go in blobFromImage. E.g. the mean subtraction values, scaling params etc. 

You can get that information from here. Now, this script only contains parameter details for a few popular models. 

So how do you get the details for other models ?

For that you would need to go to the repo of the model and look in the ReadMe section, the authors usually put that information there. 

For e.g. If I visit the github repo of the Human Pose Estimation model using this link which I got from the model downloading script.

By scrolling down the readme I can find these details here:

Note: These details are not always present in the Readme and sometimes you have to do quite some digging before you can find these parameters.

What to do if there is no GitHub repo link with the model, for e.g. this shuffleNet model does not have a GitHub link, in that case, I can see that the framework is ONNX.

So now I will visit the ONNX model zoo repo and find that model. 

After clicking on the model I will find its readme and then its preprocessing steps.

Notice that this model contains some preprocessing steps that are not supported by blobfromImage function. So this could happen and at times you would need to write custom preprocessing steps without using blobfromImage function, for e.g. in our Super Resolution post, I had to write a custom pre-processing pipeline for the network.

How to use our own Custom Trained Networks

Now that we have learned to use different models, you might wonder exactly how can we use our own custom trained models. So the thing is you can’t directly plug a trained network in a DNN module but you need to perform some operations to get a configuration file, which is why we needed a prototxt file along with the model.

Fortunately, In the next two blog posts, I plan to cover exactly this topic and show you how to use a custom trained classifier and a custom trained Detection network.

For now, you can take a look at this page which briefly describes how you can use models trained with Tensorflow Object Detection API in OpenCV.

One thing to note is that not all networks are supported by the DNN module, this is because DNN module supports some 30+ layer types, these layer names can be found at the wiki here. So if a model contains layers that are not among the supported layers then it won’t run, this is not a major issue as most common layers used in deep learning models are supported. 

Also OpenCV provides a way for you to define your own custom layers.

Using GPU’s and Faster Backends to speed up OpenCV DNN Module

By default OpenCV’s DNN module runs on the default C++ implementation which itself is pretty fast but OpenCV further allows you to change this backend to increase the speed even more.

Option 1: Use NVIDIA GPU with CUDA backend in the DNN module:

If you have an Nvidia GPU present then great, you can use that with the DNN module, you can follow my OpenCV source installation guide to configure your NVIDIA GPU for OpenCV and learn how to use it. This will make your networks run several times faster.

Option 2: Use OpenCL based INTEL GPU’s:

If you have an OpenCL based GPU then you can use that as a backend, although this increases speed but in my experience, I’ve seen speed gains only in 32 bit systems. To use the OpenCL as a backend you can see the last section of my OpenCV source installation section linked above.

Option 3: Use Halide Backend:

As described on this post from, for some time in the past using the halide backend increased the speed but then OpenCV engineer’s optimized the default C++ implementation so much that the default implementation actually got faster. So I don’t see a reason to use this backend now, Still here’s how you configure halide as a backend.

Option 4: Use Intel’s Deep Learning Inference Engine backend:

Intel’s Deep Learning Inference Engine backend is part of OpenVINO toolkit, OpenVINO stands for Open Visual Inferencing and Neural Network Optimization. OpenVINO is designed by Intel to speed up inference with neural networks, especially for tasks like classification, detection, etc. OpenVINO speeds up by optimizing the model in a hardware-agnostic way. You can learn to install OpenVINO here and here’s a nice tutorial for it.

What’s Next?

computer vision

If you want to go forward from here and learn more advanced things and go into more detail, understand theory and code of different algorithms then be sure to check out our Computer Vision & Image Processing with Python Course (Urdu/Hindi). In this course, I go into a lot of detail regarding vision fundamentals and cover a plethora of algorithms and techniques to help you master Computer Vision.

The 3 month course contains:

✔ 125 Video Lectures
✔ Discussion Forums
✔ Quizzes
✔ 100+ High Quality Jupyter notebooks
✔ Practice Assignments
✔Certificate of Completion

If you want to start a career in Computer Vision & Artificial Intelligence then this course is for you. One of the best things about this course is that the video lectures are in Urdu/Hindi Language without any compromise on quality, so there is a personal/local touch to it.


In today’s tutorial, we went over a number of things regarding OpenCV’s DNN module. From using pre-trained models to Optimizing for faster inference speed.

We also learned to perform a classification pipeline using densenet121.

This post should serve as an excellent guide for anyone trying to get started in Deep learning using OpenCV’s DNN module.

Finally, OpenCV’s DNN repo contains an example python scripts to run common networks like classification, text, object detection, and more. You can start utilizing the DNN module by using these scripts and here are a few DNN Tutorials by OpenCV.

The main contributor for the DNN module in OpenCV is Dmitry Kurtaev and formerly it was Aleksandr Rybnikov, so big thanks to them and the rest of the contributors for making such a great module.

I hope you enjoyed today’s tutorial, feel free to comment and ask questions.

Super Resolution, Going from 3x to 8x Resolution in OpenCV

Super Resolution, Going from 3x to 8x Resolution in OpenCV

A few weeks ago I published a tutorial on doing Super-resolution with OpenCV using the DNN module.

I would recommend that you go over that tutorial before reading this one but you can still easily follow along with this tutorial. For those of you who don’t know what Super-resolution is then here is an explanation.

Super Resolution can be defined as the class of Algorithms that upscales an image without losing quality, meaning you take a  low-resolution image like an image of size 224×224 and upscale it to a high-resolution version like 1792×1792 (An 8x resolution)  without any loss in quality. How cool is that?

Anyways that is Super resolution, so how is this different from the normal resizing you do?

When you normally resize or upscale an image you use Nearest Neighbor Interpolation. This just means you expand the pixels of the original image and then fill the gaps by copying the values of the nearest neighboring pixels.

The result is a pixelated version of the image.

There are better interpolation methods for resizing like bilinear or bicubic interpolation which take weighted average of neighboring pixels instead of just copying them.

Still the results are blurry and not great.

The super resolution methods enhance/enlarge the image without the loss of quality, Again, for more details on the theory of super resolution methods, I would recommend that you read my Super Resolution with OpenCV Tutorial.

In the above tutorial I describe several architectural improvements that happened with SR Networks over the years.

But unfortunately in that tutorial, I only showed you guys a single SR model which was good but it only did a 3x resolution. It was also from a 2016 paper Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network” 

That all changes now, in this tutorial we will work with multiple models, even those that will do 8x resolution.

Today, we won’t be using the DNN module, we could do that but for the super resolution problem OpenCV comes with a special module called dnn_superres which is designed to use 4 different powerful super resolution networks. One of the best things about this module is that It does the required pre and post processing internally, so with only a few lines of code you can do super resolution.

The 4 models we are going to use are:

  • EDSR: Enhanced Deep Residual Network from the paper Enhanced Deep Residual Networks for Single Image Super-Resolution (CVPR 2017) by Bee Lim et al.

  • ESPCN: Efficient Subpixel Convolutional Network from the paper Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR 2016) by Wenzhe Shi et al.

  • FSRCNN: Fast Super-Resolution Convolutional Neural Networks from the paper Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016) by Chao Dong et al.

  • LapSRN: Laplacian Pyramid Super-Resolution Network from the paper Deep Laplacian pyramid networks for fast and accurate super-resolution (CVPR 2017) by Wei-Sheng Lai et al.

Here are the papers for the models and some extra resources.

Make sure to download the zip folder from the download code section above. As you can see by clicking the Download models link that each model has different versions like 3x, 4x etc. This means that the model can perform 3x resolution, 4x resolution of the image, and so on. The download zip that I provide contains only a single version of each of the 4 models above.

You can feel free to test out other models by downloading them. These models should be present in your working directory if you want to use them with the dnn_superres module.

Now the inclusion of this super easy to use dnn_superres module is the result of the work of 2 developers Xavier Weber and Fanny Monori. They developed this module as part of their GSOC (Google summer of code) project. GSOC 2019 also made NVIDIA GPU support possible. 

It’s always amazing to see how a summer project for students by google brings forward some great developers making awesome contributions to the largest Computer Vision library out there.

The dnn_superes module in OpenCV was included in version 4.1.2  for C++ but the python wrappers were added in 4.3 version about a month back, so you have to make sure that you have OpenCV version 4.3 installed. And of course, since this module is included in the contrib module so make sure you have also installed OpenCV contrib package.


Note: You can’t install OpenCV 4.3 version by doing pip install as the latest version here open-contrib-python from pip is still version

So the pypi version of OpenCV is maintained by just one guy named: Olli-Pekka Heinisuo by username: skvark and he updates the pypi OpenCV package in his free time. Currently, he’s facing a compiling issue which is why 4.3 version has not come out as of 7-15-2020. But from what I have read, he will be building the .whl files for 4.3 version soon, it may be out this month. If that happens then I’ll update this post.

So right now the only way you will be able to use this module is if you have installed OpenCV 4.3 from Source. If you haven’t done that then you can easily follow my installation tutorial.

I should also take this moment to highlight the fact you should not always rely on OpenCV’s pypi package, no doubt skvark has been doing a tremendous job maintaining OpenCV’s pypi repo but this issue tells you that you can’t rely on  a single developer’s free time to update the library for production use cases, learn to install the Official library from source. Still, pip install opencv-contrib-python is a huge blessing for people starting out or in early stages of learning OpenCV, so hats off to skvark.

As you might have noticed among the 4 models above we have already learned to use ESPCNN in the previous tutorial, we will use it again but this time with the dnn_superres module.

Super Resolution with dnn_superres Code

Download Code for this post

Download Code for this post

Directory Hierarchy

After downloading the zip folder, unzip it and you will have the following directory structure.

This is how our directory structure looks like, it has a Jupyter notebook, a media folder with images and the model folder containing all 4 models.

You can now run the notebook Super_Resolution_with_dnn_superres.ipynb and start executing each cell as follows.

Import Libraries

Start by Importing the required libraries.

Initialize the Super Resolution Object

First you have to create the dnn_superres constructor by the following command.

Read Image

We will start by reading and displaying a sample image. We will be running the EDSR model (with 4x scale) to upscale this image.

Extracting Model Name & Scale

In the next few steps, will be using a setModel() function in which we will pass the model’s name and its scale. We could manually do that but all this information is already present in the model’s pathname so we just need to extract the model’s name and scale using simple text processing.

model name: edsr
model scale: 4

Reading the model

Finally we will read the model, this is where all the required weights of the model gets loaded. This is equivalent to DNN module’s readnet function

Setting Model Name & Scale

Here we are setting the name and scale of the model which we extracted above.

Why do we need to do that ?

So remember when I said that this module does not require us to do preprocessing or postprocessing because it does that internally. So in order to initiate the correct pre and post-processing pipelines, the module needs to know which model we will be using and what version meaning what scale 2x, 3x, 4x etc.

Running the Network

This is where all the magic happens. In this line a forward pass of the network is performed along with required pre and post-processing. We are also making note of the time taken as this information will tell us if the model can be run in real-time or not.

As you can see it takes a lot of time, in fact, EDSR is the most expensive model out of the four in terms of computation.

It should be noted that larger your input image’s resolution is the more time its going to take in this step.

Wall time: 45.1 s

Check the Shapes

We’re also checking the shapes of the original image and the super resolution image. As you can see the model upscaled the image by 4 times.

Shape of Original Image: (262, 347, 3) , Shape of Super Resolution Image: (1200, 1200, 3)

Comparing the Original Image & Result

Finally we will display the original image along with its super resolution version. Observe the difference in Quality.

Save the High Resolution Image

Although you can see the improvement in quality but still you can’t observe the true difference with matplotlib so its recommended that you save the SR image in disk and then look at it.

Creating Functions

Now that we have seen a step by step implementation of the whole pipeline, we’ll create the 2 following python functions so we can use different models on different images by just calling a function and passing some parameters.

Initialization Function: This function will contain parts of the network that will be set once, like loading the model.

Main Function: This function will contain the rest of the code. it will also have the option to either return the image or display it with matplotlib. We can also use this function to process a real-time video.

Initialization Function

Main Function

Set returndata = True when you just want the image. This is usually done when I’m working with videos. I’ve also added a few more optional variables to the method.

print_shape: This variable decides if you want to print out the shape of the model’s output.

name: This is the name by which you will save the image in disk.

save_img: This variable decides if you want to save the images in disk or not.

Now that we have created the initialization function and a main function, lets use all 4 models on different examples

The function above displays the original image along with the SR Image.

Initialize Enhanced Deep Residual Network (EDSR, 4x Resolution)

Run the network

Shape of Original Image: (221, 283, 3) , Shape of Super Resolution Image: (884, 1132, 3)
Wall time: 43.1 s

Initialize Efficient Subpixel Convolutional Network (ESPCN, 4x Resolution)

Run the network

Shape of Original Image: (256, 256, 3) , Shape of Super Resolution Image: (1024, 1024, 3)
Wall time: 295 ms

Initialize Fast Super-Resolution Convolutional Neural Networks (FSRCNN, 3x Resolution)

Run the network

Shape of Original Image: (232, 270, 3) , Shape of Super Resolution Image: (696, 810, 3)
Wall time: 253 ms

Initialize Laplacian Pyramid Super-Resolution Network (LapSRN, 8x Resolution)

Run the network

Shape of Original Image: (302, 357, 3) , Shape of Super Resolution Image: (2416, 2856, 3)
Wall time: 26 s

Applying Super Resolution on Video

Lastly, I’m also providing the code to run Super-resolution on Videos. Although the example video I’ve used sucks, but that’s the only video I tested on primarily because I’m only interested in doing super resolution on images as this is where most of my use cases lie. Feel free to test out different models for real-time feed.

Tip: You might also want to save the High res video in disk using the VideoWriter Class.


Here’s a chart for benchmarks using a 768×512 image with 4x resolution on an Intel i7-9700K CPU for all models.

The benchmark shows PSNR (Peak signal to noise ratio) and SSIM (structural similarity index measure) scores, these are the scores which measure how good the supre res network’s output is.

The best performing model is EDSR but it has the slowest inference time, the rest of the models can work in real time.

For detailed benchmarks you can see this page.  Also make sure to check Official OpenCV contrib page on dnn_superres module

If you thought upscaling to 8x resolution was cool then take a guess on the scaling ability of the current state of the Art algorithm in super-resolution?

So believe it or not the state of the art in SR can actually do a 64x resolution…yes 64x, that wasn’t a typo.

In fact, the model that does 64x was published just last month, here’s the paper for that model, here’s the GitHub repo and here is a ready to run colab notebook to test out the code. Also here’s a video demo of it. It’s pretty rare that such good stuff is easily accessible for programmers just a month after publication so make sure to check it out.

The model is far too complex to explain in this post but the authors took a totally different approach, instead of using supervised learning they used self-supervised learning. (This seems to be on the rise).

What’s Next?

computer vision

If you want to go forward from here and learn more advanced things and go into more detail, understand theory and code of different algorithms then be sure to check out our Computer Vision & Image Processing with Python Course (Urdu/Hindi). In this course, I go into a lot of detail regarding vision fundamentals and cover a plethora of algorithms and techniques to help you master Computer Vision.

The 3 month course contains:

✔ 125 Video Lectures
✔ Discussion Forums
✔ Quizzes
✔ 100+ High Quality Jupyter notebooks
✔ Practice Assignments
✔Certificate of Completion

If you want to start a career in Computer Vision & Artificial Intelligence then this course is for you. One of the best things about this course is that the video lectures are in Urdu/Hindi Language without any compromise on quality, so there is a personal/local touch to it.


In today’s tutorial we learned to use 4 different architectures to do Super resolution going from 3x to 8x resolution. 

Since the library handles preprocessing and postprocessing, so the code for all the models was almost the same and pretty short.

As I mentioned earlier, I only showed you results of a single version of each model, you should go ahead and try other versions of each model.

These models have been trained using DIV2K  BSDS and General100 datasets which contains images of diverse objects but the best results from a super-resolution model is obtained by training them for a domain-specific task, for e.g if you want the SR model to perform best on pedestrians then your dataset should consist mostly of pedestrian images. The best part about training SR networks is that you don’t need to spend hours doing manual annotation, you can just resize them and you’re all set.

Also I would raise a concern regarding these models that we must be careful using SR networks, for e.g. consider this scenario:

 You caught an image of a thief stealing your mail on your low res front door cam, the image looks blurry and you can’t make out who’s in the image.

Now you being a Computer Vision enthusiast thought of running a super res network to get a clearer picture.
After running the network, you get a much clearer image and you can almost swear that it’s Joe from the next block.

The same Joe that you thought was a friend of yours.

The same Joe that made different poses to help you create a pedestrian datasets for that SR network you’re using right now.

How could Joe do this?

Now you feel betrayed but yet you feel really Smart, you solved a crime with AI right?

You Start STORMING to Joe’s house to confront him with PROOF.

Now hold on! … like really hold on.

Don’t do that, seriously don’t do that.

Why did I go on a rant like that?

Well to be honest back when I initially learned about SR networks that’s almost exactly what I thought I would do. Solve Crimes by AI by doing just that (I know it was a ridiculous idea). But soon I realize that SR networks only learn to hallucinate data based on learned data, they can’t visualize a face with 100% accuracy that they’ve never seen. It’s still pretty useful but you have to use this technology carefully.

I hope you enjoyed this tutorial, feel free to comment below and I’ll gladly reply.

Emotion / Facial Expression Recognition with OpenCV.

Emotion / Facial Expression Recognition with OpenCV.

A few weeks ago we learned how to do Super-Resolution using OpenCV’s DNN module, in today’s post we will perform Facial Expression Recognition AKA Emotion Recognition using the DNN module. Although the term emotion recognition is technically incorrect (I will explain why) for this problem but for the remainder of this post I’ll be using both of these terms, since emotion recognition is short and also good for SEO since people still search for emotion recognition while looking for facial expression recognition xD.

The post is structured in the following way:

  • First I will define Emotion Recognition & its importance.
  • Then I will discuss different approaches to tackle this problem.
  • Finally, we will Implement an Emotion Recognition pipeline using OpenCV’s DNN module. 

Emotion Recognition Or Facial Expression Recognition

Now let me start by clarifying what I meant when I said this problem is incorrectly quoted as Emotion recognition. So you see by saying that you’re doing emotion recognition you’re implying that you’re actually finding the emotion of a person whereas in a typical AI-based emotion recognition system you’ll find around and the one that we’re gonna built looks only at a single image of a person’s face to determine the emotion of that person. Now, in reality, our expression may at times exhibit what we feel but not always. People may smile for a picture or someone may have a face that inherently looks gloomy & sad but that doesn’t represent the person’s emotion. 

So If we were to build a system that actually recognizes the emotions of a person then we need to do more than look at a simple face image. We would also consider the body language of a person through a series of frames, so the network would be a combination of an LSTM & a CNN network. Also for a more robust system, we may also incorporate a voice tone recognition AI as the tone of a voice, and speech patterns tell a lot about the person’s feelings.

Watch this part of the interview of Lisa Feldman Barret who debunks these so-called Emotion recognition systems.

Since today we’ll only be looking at a single face image so it’s better to call our task Facial Expression Recognition rather than Emotion recognition.

Facial Expression Recognition Applications:

Monitoring facial expressions of several people over a period of time provides great insights if used carefully, so for this reason we can use this technology in the following applications.

1: Smart Music players that play music according to your mood:

Think about it, you come home after having a really bad day, you lie down on the bed looking really sad & gloomy and then suddenly just the right music plays to lift up your mood.

2: Student Mood Monitoring System:

Now a system that cleverly averages the expressions of multiple students over a period of time can get an estimate of how a particular topic or teacher is impacting students, does the topic being taught stresses out the students, is a particular session from a teacher a joyful experience for students. 

3: Smart Advertisement Banners:

Think about smart advertisement banners that have a camera attached to it, when a commercial airs, it checks real-time facial expressions of people consuming that ad and informing the advertiser if the ad had the desired effect or not. Similarly, companies can get feedback if customers liked their products or not without even asking them.

Also, check out this video in which the performance of a new Ice Cream flavor is tested on people using their expressions.

These are just some of the applications from top of my head, if you start thinking about it you can come up with more use cases. One thing to remember is that you have to be really careful as how you use this technology. Use it as an assistive tool and do not completely rely on it. For e.g don’t deploy on Airport and start interrogating every other black guy who triggers Angry expressions on the system for a couple of frames.

Facial Expression Recognition Approaches:

So let’s talk about the ways we could go about recognizing someone’s facial expressions. We will look at some classical approaches first then move on to deep learning.

Haar Cascades based Recognition:

Perhaps the oldest method that could work are Haar Cascades. So essentially these Haar Cascades also called viola jones Classifier is an outdated Object detection technique by Paul Viola and Michael Jones in 2001. It is a machine learning-based approach where a cascade is trained from a lot of positive and negative images. It is then used to detect objects in images.

The most popular use of these cascades is as a face detector which is still used today, although there are better methods available. 

Now instead of using face detection, we could train a cascade to detect expressions. Since you can only train a single class with a cascade so you’ll need multiple cascades. A better way to go about is to first perform face detection then look for different features inside the face ROI, like detecting a smile with this smile detection cascade. You can also train a frown detector and so on.

Truth be told, this method is so weak that I wouldn’t even try experimenting with this in this time and era but since people have used this in the past so I’m just putting it there.

Fisher, Eigen & LBPH based Recognition:

OpenCV’s built-in face_recognition module has 3 different face recognition algorithms, Eigenfaces face recognizer,  Fisherfaces face recognizer and Local binary patterns histograms (LBPH) Face Recognizer.

If you’re wondering why am I mentioning face recognition algorithms on a facial expression recognition post, So understand this,  these algorithms can extract some really interesting features like principal components and local histograms which you can then feed into an ML classifier like SVM, so in theory, you can repurpose them for emotion recognition, only this time the target classes are not the identities of people but some facial expressions. This will work best if you have a few classes, ideally 2-3. I haven’t seen many people work on emotion like this but take a look at this post in which a guy uses Fisher faces for facial expression recognition.

Again I would mention this is not a robust approach, but would work better than the previous one.

Histogram Oriented Gradients based Recognition (HOG):

Now similar to the above approach instead of using the face_recognizer module to extract features you can extract HOG features of faces, HOG based features are really effective. After extracting HOG features you can train an SVM or any other Machine learning classifier on top of it.

Custom Features with Landmark Detection:

One of the easiest and effective ways to create an emotion recognition system is to use a landmark detector like the one in dlib which allows you to detect 68 important landmarks on the face.

By using this detector you can extract facial features like eyes, eyebrows, mouth, etc. Now you can take custom measurements of these features like measuring the distance between the lip ends to detect if the person is smiling or not. Similarly, you can measure if the eyes are wide open or not, indicating surprise or shock.

Now there are two ways to go about it, either you can send these custom measurements to an ML classifier and let it learn to predict emotions based on these measurements or you use your own heuristics to determine when to call it happy, sad etc based on the measurements.

I do think the former approach is more effective than the latter. But if you’re just determining a singular emotion like if a person is smiling or not then it’s easier to use heuristics.

Deep Learning based Recognizer:

It should not come as a surprise that the State of the Art approach to detect emotions would be a deep learning-based approach. Let me explain how you would create a simple yet effective emotion recognizer system. So what you would simply do is train a Convolutional Neural Network (CNN) on different facial expression images (Ideally thousands of images for each class/emotion) and after the training showed it new samples and if done right it would perform better than all the above approaches I’ve mentioned.

Now that we have discussed different approaches, let’s move on to the coding part of the blog. 

Facial Expression Recognition in OpenCV

We will be using a deep learning classifier that will be loaded to the OpenCV DNN module. The authors trained this model using MS Cognitive Toolkit (formerly CNTK) and then converted this model to ONNX (Open neural network exchange ) format.

ONNX format allows developers to move models between different frameworks such as CNTK, Caffe2, Tensorflow, PyTorch etc.

There is also a javascript version of this model (version 1.2) with a live demo which you can check out here. In this post we will be using version 1.3 which has a better performance.

You can also look at the original source code used to train this model here, the authors explained the architectural details of their model in their research paper titled Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution.

In the paper, the authors demonstrate training a deep CNN using 4 different approaches: majority voting, multi-label learning, probabilistic label drawing, and cross-entropy loss. The model that we are going to use today was trained using cross-entropy loss, which according to the author’s conclusion was one of the best performing models.

The model was trained on FER+ dataset,  FER dataset was the standard dataset for emotion recognition task but in FER+ each image has been labeled by 10 crowd-sourced taggers, which provides a better quality of ground truth label for still image emotion than the original FER labels.

More information about the ONNX version of the model can be found here.

The input to our emotion recognition model is a grayscale image of 64×64 resolution. The output is the probabilities of 8 emotion classes: neutral, happiness, surprise, sadness, anger, disgust, fear, and contempt.

Here’s the architecture of the model.

Here are the steps we would need to perform:

  1.  Initialize the Dnn module.
  2. Read the image.
  3. Detect faces in the image.
  4. Pre-process all the faces.
  5. Run a forward pass on all the faces.
  6. Get the predicted emotion scores and convert them to probabilities.
  7. Finally get the emotion corresponding to the highest probability

Make sure you have the following Libraries Installed.

  • OpenCV ( possibly Version 4.0 or above)
  • Numpy
  • Matplotlib
  • bleedfacedetector

Bleedfacedetector is my face detection library which can detect faces using 4 different algorithms. You can read more about the library here.

You can install it by doing:

pip install bleedfacedetector

Before installing bleedfacedetector make sure you have OpenCV & Dlib installed.

pip install opencv-contrib-python

To install dlib you can do:

pip install dlib
pip install dlib==19.8.1

Download Code for this post

Download Resource Guide for this post

Directory Hierarchy

You can go ahead and download the source code from the download code section. After downloading the zip folder, unzip it and you will have the following directory structure.

You can now run the Jupyter notebook Facial Expression Recognition.ipynb and start executing each cell as follows.

Import Libraries

Initialize DNN Module

To use Models in ONNX format, you just have to use cv2.dnn.readNetFromONNX(model) and pass the model inside this function.

Read Image

This is our image on which we are going to perform emotion recognition.

  • Line 2: We’re reading the image form disk.
  • Line 5-6 : We’re setting the figure size and showing the image with matplotlib, [:,:,::-1] means to reverse image channels so we can show OpenCV BGR images properly in matplotlib. OpenCV BGR images.

Define the available classes / labels

Now we will create a list of all 8 available emotions that we need to detect.

Detect faces in the image

The next step is to detect all the faces in the image, since our target image only contains a single face so we will extract the first face we find. 

Line 4: We’re using an SSD based face detector with 20% filter confidence to detect faces, you can easily swap this detector with any other detector inside bleedfacedetector by just changing this line.

Line 7: We’re extracting the x,y,w,h coordinates from the first face we found in the list of faces.

Line 10-13: We’re padding the face by a value of 3, now this expands the face ROI boundaries, this way the model takes a look at a larger face image when predicting. I’ve seen this improves results in a lot of cases, Although this is not required.

Padded Vs Non Padded Face

Here you can see what the final face ROI looks like when it’s padded and when it’s not padded.

Pre-Processing Image

Before you pass the image to a neural network you perform some image processing to get the image in the right format. So the first thing we need to do is convert the face from BGR to Grayscale then we’ll resize the image to be of size 64x64. This is the size that our network requires. After that we’ll reshape the face image into (1, 1, 64, 64), this is the final format which the network will accept.

Line 2: Convert the padded face into GrayScale image
Line 5: Resize the GrayScale image into 64 x 64
Line 8: Finally we are reshaping the image into the required format for our model

Input the preprocessed Image to the Network

Forward Pass

Most of the Computations will take place in this step, This is the step where the image goes through the whole neural network.

Check the output

As you can see, the model outputs scores for each emotion class.

Shape of Output: (1, 8)
[[ 0.59999390 -0.05662632 7.5.22 -3.5109.508 -0.33268.593 -3.967.581.5 9.2001578 -3.1812003 ]]

Apply Softmax function to get probabilities:

We will convert the model scores to class probabilities between 0-1 by applying a Softmax function on it.

[9.1010029e-04 4.7197891e-04 9.6490067e-01 1.491846e-05
3.5819356e-04 9.4487186e-06 3.3313509e-02 2.1165248e-05]

Get Predicted emotion

Predicted Emotion is: Surprise

Display Final Result

We already have the correct prediction from the last step but to make it more cleaner we will display the final image with the predicted emotion, we will also draw a bounding box over the detected face.

Creating Functions

Now that we have seen a step by step implementation of the network, we’ll create the 2 following python functions.

Initialization Function: This function will contain parts of the network that will be set once, like loading the model.

Main Function: This function will contain all the rest of the code from preprocessing to postprocessing, it will also have the option to either return the image or display it with matplotlib.

Furthermore, the Main Function will be able to predict the emotions of multiple people in a single image, as we will be doing all the operations in a loop.

Initialization Function

Main Function

Set returndata = True when you just want the image. I usually do this when working with videos.

Initialize the Emotion Recognition

Call the initialization function once.

Calling the main function

Now pass in any image to the main function 

Real time emotion recognition on Video:

You can also take the above main function that we created and put it inside a loop and it will start detecting facial expressions on a video, below code detects emotions using your webcam in real time. Make sure to set returndata = True


Here’s the confusion matrix of the model from the author’s paper. As you can see this model is not good at predicting Disgust, Fear & Contempt classes.

You can try running the model on different images and you’ll also agree with the above matrix, that the last three classes are pretty difficult to predict, particularly because It’s also hard for us to differentiate between these many emotions based on just facial expression, a lot of micro expressions overlap between these classes and so it’s understandable why the algorithm would have a hard time differentiating between 8 different emotional expressions.

Improvement Suggestions:

Still, if you really want to detect some expressions that the model seems to fail on then the best way to go about is to train the model yourself on your own data. Ethnicity & color can make a lot of difference. Also, try removing some emotion classes so the model can focus only on those that you care about.

You can also try changing the padding value, this seems to help in some cases.

If you’re working on a live video feed then try to average the results of several frames instead of giving a new result on every new frame. 

What’s Next?

computer vision

If you want to go forward from here and learn more advanced things and go into more detail, understand theory and code of different algorithms then be sure to check out our Computer Vision & Image Processing with Python Course (Urdu/Hindi). In this course, I go into a lot of detail regarding vision fundamentals and cover a plethora of algorithms and techniques to help you master Computer Vision.

The 3 month course contains:

✔ 125 Video Lectures
✔ Discussion Forums
✔ Quizzes
✔ 100+ High Quality Jupyter notebooks
✔ Practice Assignments
✔Certificate of Completion

If you want to start a career in Computer Vision & Artificial Intelligence then this course is for you. One of the best things about this course is that the video lectures are in Urdu/Hindi Language without any compromise on quality, so there is a personal/local touch to it.


In this tutorial we first learned about the Emotion Recognition problem, why it’s important, and what are the different approaches we could take to develop such systems.

Then we learned to perform emotion recognition using OpenCV’s DNN module. After that, we went over some ways on how to improve our results.

I hope you enjoyed this tutorial. If you have any questions regarding this post then please feel free to comment below and I’ll gladly answer them.

Computer Vision Crash Course with OpenCV & Python

Computer Vision Crash Course with OpenCV & Python

computer vision

If you’re looking for a single stand-alone Tutorial that will give you a good overall taste of the exciting field of Computer Vision using OpenCV then this is it. This Tutorial will serve as a Crash Course to learn the basics of OpenCV Library. 

What is OpenCV:

OpenCV (Open Source Computer Vision ) is the biggest library for Computer Vision which contains more than 2500 optimized algorithms that can be used to do face detection, action recognition, image stitching, extracting 3d models, generating point clouds, augmented reality and a lot more.

So if you’re planning to perform Computer Vision weather on a deep learning project or on a Raspberry pie or you want to make a career in it then at some point you will definitely cross paths with this library. So it’s better that you get started with it today.

About this Crash Course Course:

Since I’m a member of the Official Course team and this blog Bleed AI is all about making you master Computer Vision, so I feel I’m in a very good position to teach you about this library and that too in a single post.

Of Course, we won’t be able to cover a whole lot as I said it contains over 2500 algorithms, still, after going through this course you will be able to get a grip on fundamentals and built some interesting things.

Prerequisite: To follow along with this course it’s important that you are familiar with Python language & you have python installed in your system.

Make sure to download the Source code below to try out the code.

Download Code for this post

Download Resource Guide for this post

Let’s get Started

Crash Course Outline:

Here’s the outline for this course.

Installing OpenCV-python:

The easiest way to install OpenCV is by using a package manager like e.g. with pip.

So you can just Open Up the command prompt and run the following command:

pip install opencv-contrib-python

By doing the above, you will install opencv along with its contrib package which contains some extra algorithms. If you don’t need the extra algorithms then you can also run the following command:

pip install opencv-python

Make sure to install Only one of the above packages, not both. There are also some headless versions of OpenCV which do not contain any GUI functions, you can look those here.

The other Method to install OpenCV is installing it from the source. Now installing from the source has its perks but it’s much harder and I recommend only people who have prior experience with OpenCV attempting this. You can look at my tutorial of installing from the source here.

Note: Before you can install OpenCV, you must have numpy library installed on your system. You can install numpy by doing:

pip install numpy

After Installing OpenCV you should check your installation by opening up the command prompt or anaconda prompt, launching python interpreter by typing python and then importing OpenCV by doing: import cv2

Reading & Displaying an Image:

After installing OpenCV we will see how we can read & display an image in OpenCV. You can start by running the following cell in the jupyter notebook you downloaded from the source code section.

In OpenCV you can read an image by using the cv2.imread() function. 

image = cv2.imread(filename, [flag])

Note: The Square brackets i.e. [ ] are used to denote optional parameters


  • filename: Name of the image or path to the image.
  • flag: There are numerous flags but three most important ones are these: 0,1,-1

If you pass in 1 the image is read in Color, if 0 is passed the image is read in Grayscale (Black & white) and if -1 is used to read transparent images which we will learn in the next chapter, If no parameter is passed the image will be read in Color.

Line 1-5: Importing Opencv and numpy library.
Line 8: We are reading our image in grayscale, this function will read the image in a numpy array format.
Line 11: We are printing our image.


Now just by looking at the above output, you can get a lot of information about the image we used.

Take a guess on what’s written in the image

Go ahead …I’ll wait.

If you guessed the number 2 then congrats you’re right. In fact, there is a lot more information that you can extract from the above output. For e.g, I can tell that the size of the image is (21x22). I can also say that number 2 is written in white on a black image and is written in the middle of the image.

How was I able to get all that…especially considering I’m no Sherlock?

The size of the image can easily be extracted by counting the number of rows & columns. And since we are working with a single channel grayscale image, the values in the image represent the intensity of the image, meaning 0 represents black and 255 white color, and all the numbers between 0 and 255 are different shades of gray.

You can look at the colormap below of a Grayscale image to understand it better.

Beside’s counting the rows and columns, you can just use the shape function on a numpy array to find its shape


(21, 22)

The values returned are in rows, columns or you can call it height, width, or x,y. If we were dealing with a color image then img.shape would have returned height, width, channels.

Now it’s not ideal to print images, especially when they are 100s of pixels in width and height, so let’s see how we can show images with OpenCV.

To display an Image there are generally 3 steps. There are generally 3 steps involved in displaying an image properly.

Step 1: Use cv2.imshow() to show images.

cv2.imshow(Window_Name, img)


  • Window_Name: Any custom name you  assign to your window
  • img: Your image either be in uint8 datatype or float datatype having range 0-1.

Step 2: Also with cv2.imshow() you will have to use the cv2.waitKey() function. This function is a keyboard binding function. Its argument is the time in milliseconds. The function waits for specified milliseconds. If you press any key in that time frame, the program continues. If 0 is passed, it waits indefinitely for a keystroke. This function returns the ASCII value of the keyboard key pressed, for e.g. if you press ESC key then it will return 27 which is the ASCII value for the ESC key. For now, we won’t be using this returned value.


Note: The default delay is 0 which means wait forever until the user presses a key.

Step 3: The last step is to destroy the window we created so the program can end, now this is not required to view the image but if you don’t destroy the window then you can’t proceed to end the program and it can crash, so to destroy the windows you will do:


This will destroy all present image windows, there is also a function to destroy a specific window.
Now let’s see the full code in action.

Line 5: I’m resizing the image by 1000%  or by 10 times in both x and y direction using the function cv2.resize() since the original size of the image is too small. I will later discuss this function.
Line 8-14:  Showing the image and waiting for a keypress. Destroying the image when there is a keypress.


Accessing & Modifying Image Pixels and ROI:

For this example, I will be reading this image which is from one of my favorite Anime series.

You can access individual pixels of the image and modify them. Now before we get into that lets understand how an image is represented in OpenCV. We already know it’s a numpy array. But besides that you can find out other properties of the image.


The data type of the Image is: uint8
The dimensions of the Image is: 3

So the datatype of images you read with OpenCV is uint8 and if its a color image then it’s a 3-dimensional image.
Let’s talk about these dimensions. First 2 are the width and the height and the 3rd are the image channels. Now these are B (blue), G (green), & R (red) channels. In OpenCV due to historical reasons, colored images are stored in BGR instead of the common RGB format.

You can access any individual pixel value bypassing its x,y location in the image.


[143 161 168]

The tuple output above means that at location (300,300) the value for the blue channel is 143, the green channel is 161 and the red channel is 168.

Just like we can read individual image pixels, we can modify them too.

I’ve just made the pixel at location (300,300) black. Because I’ve only modified a single pixel the change is really hard to see. So now we will modify an ROI (Region of Interest) of the image so that we can see our changes.

Modifying a whole ROI is pretty similar to modifying a pixel, you just need to select a range instead of a single value.

Line 1-2: We are making a copy of the image so we don’t end up modifying the original.

Line 4-5: We are setting all pixels in x range 100-150 and in y range 80-120 equal to 0 (meaning black). Now, this should give us a black box in the image.

Line 8-10 :  Showing the image and waiting for a keypress. Destroying the image when there is a keypress.


Resizing an Image:

You can use cv2.resize() function to resize an image. You have 2 ways of resizing the image, either by passing in the new width & height values or by passing in percentages of those values using fx and fy params. We have already seen how we used the second method to resize the image to 10x its size so now I’m going to show you the first method.

You can see below both the original and the resized version of the image.


An obvious problem with the above approach you can see is that it’s not maintaining the aspect ratio of the image which is why the image looks distorted to you. A better approach would be to resize a single dimension at a time and shrink or expand the other dimension accordingly.

Resizing While Keeping the Aspect Ratio Constant:

So let’s resize the image while keeping the aspect ratio constant. This time we are going to resize the width to 300 and modify the height respectively.

Line 4-5: We are extracting the shape of the image, [:-1] indicates that I don’t want channels returned, just height and width. This ensures your code works for both color and grayscale images.

Line 7-11: We are calculating the ratio of the new width to the old width and then multiplying this ratio value with the height for getting the new value of the height. The logic behind is this, if we resized a 600 px width image to 300 px width then we would get a ratio of 0.5 and if the height was 200 px then by multiplying 0.5 with the height, we would get a new value of 100 px, by using these new values we won’t get any distortions.


Geometric Transformations:

You can apply different kinds of transformations to the image, now there are some complex transformations but for this post, I will only be discussing translation & rotation. Both of these are types of Affine transformations. So we will be using a function called warpAffine() to transform them.

transformed_ image = cv2.warpAffine(src, M, dsize[, dst[, flags[, borderMode[, borderValue]]]])


  • src: input image.
  • M: 2×3 transformation matrix.
  • dsize: size of the output image.
  • flags: combination of interpolation methods.
  • borderMode: pixel extrapolation method (see BorderTypes) by default its constant border.
  • borderValue: value used in case of a constant border; by default, it is 0, which means replaced values will be black.

Now you pass in a 2×3 Matrix into the warpaffine function which does the required transformation, the first two 2 columns of the matrix control, rotation, scale and shear, and the last column encodes translation (shift) of image.

Again, we will only focus on translation and rotation in this post.


Translation is the shifting of an object’s location, meaning the movement of image in x, y-direction. Suppose you want the image to move tx amount of pixels in the x-direction and ty amount of pixels in y-direction then you will construct below transformation matrix accordingly and pass it into the warpAffine function.

So now you just need to change the tx and ty values here for translation in x and y direction.

Line 6-10: We’re constructing the translation matrix so we move 120 px in x-direction and 40 px in the negative y-direction.



Similarly, we can also rotate an image, by passing a matrix into the warpaffine function. Now instead of designing a matrix for rotation, I’m going to use a built-in function called cv2.getRotationMatrix2D() which will return a rotation matrix according to our specifications.

M = cv2.getRotationMatrix2D( center, angle, scale )


  • center: This is the center of the rotation in the source image.
  • Angle: The Rotation angle in degrees. Positive values mean counter-clockwise rotation (the coordinate origin is assumed to be the – top-left corner).
  • Scale: scaling factor.


Note: If you don’t like the black pixels that appear after translation or rotation then you can use a different border filling method, look at the available borderModes here.

Drawing on Image:

Let’s take a look at some drawing operations in OpenCV. So now we will learn how to draw a line, a circle, and a rectangle on an image. We will also learn to put text on the image. Since each drawing function will modify the image so we will be working on copies of the original image. We can easily make a copy of image by doing: img.copy()

Most of the drawing functions have below parameters in common.

  • img : Your Input Image
  • color : Color of the shape for a BGR image, pass it as a tuple i.e. (255,0,0), for Grayscale image just pass a single scalar value from 0-255.
  • thickness : Thickness of the line or circle etc. If -1 is passed for closed figures like circles, it will fill the shape. default thickness = 1
  • lineType : Type of line, popular choice is cv2.LINE_AA .

Drawing a Line:

We can draw a line in OpenCV by using the function cv2.line(). We know from basic geometry you can draw a line, you just need 2 points. So you’ll pass in coordinates of 2 points in this function.

cv2.line(img, pt1, pt2, color, [thickness])


  • pt1: First point of the line, this is a tuple of (x1,y1) point.
  • pt2: Second point of the line, this is a tuple of (x2,y2) point.


Drawing a Circle

We can draw a Circle in OpenCV by using the function cv2.Circle(). For drawing a circle we just need a center point and a radius., Center, radius, color, [thickness])


  • center: Center of the circle.
  • radius: Radius of the circle.


Drawing a Rectangle

We can also draw a rectangle in OpenCV by using the function cv2.rectangle(). You just have to pass two corners of a rectangle to draw it. It’s similar to the cv2.line function.

cv2.rectangle(img, pt1, pt2, color, [thickness])


  • pt1: Top left corner of the rectangle.
  • pt2: bottom right corner of the rectangle.


Putting Text:

Finally, we can also write Text by using the function cv2.putText(). Writing Text on images is an essential tool, you will be able to see real-time stats on image instead of just printing. This is really handy when you’re working with videos.

cv2.putText(img, text, origin, fontFace, fontScale, color, [thickness])


  • text: Text string to be drawn.
  • origin: Top-left corner of the text (x,y) origin position.
  • fontFace: Font type, we will use cv2.FONT_HERSHEY_SIMPLEX.
  • fontScale: Font scale, how large your text will be.


Cropping an Image:

We can also crop or slice an image, meaning we can extract any specific area of the image using its coordinates, the only condition is that it must be a rectangular area. You can segment irregular parts of images but the image is always stored as a rectangular object in the computer, this should not be a surprise since we already know that images are matrices. Now let’s say we wanted to crop naruto’s face then we would need four values namely X1 (lower bound on the x-axis),  X2 (Upper bound on y-axis), Y1 (lower bound on the y-axis) and Y2 (Upper bound on the y-axis)

After getting these values, you will pass them in like below.

face_roi = img [Start X : End X, Start Y: End Y]

Lets see the full script

Line 2: We are passing in the coordinates to crop naruto’s face, you can get these coordinates by several methods, some are of them are: by trial and error, by hovering the mouse over the image when using matplotlib notebook magic command, or by hovering over the image when you have installed OpenCV with QT support or by making a mouse click function that splits x,y coordinates. 


Note: If you’re gonna modify the cropped ROI, then it’s better to make a copy of it, otherwise modifying the cropped version would also affect the original. 

You can make a copy like this:

face_roi  = img[100:270,300:450].copy()

Image Smoothing/Blurring:

Smoothing or blurring an Image in OpenCV is really easy. If you’re thinking about why we would need to blur an image then understand that It’s very common to blur/smooth an image in vision applications, this reduces noise in the image. The noise can be present due to various factors like maybe the sensor by which you took the picture was corrupted or it malfunctioned, or environmental factors like the lightning was poor, etc. Now there are different types of blurring to deal with different types of noises and I have discussed each method in detail and even done a comparison between them inside our Computer Vision Course but for now, we will briefly look at just one method, the Gaussian Blurring method. This is the most common image smoothing technique used. It gets rid of Gaussian Noise. In simple words, this will work most of the time. 

Smoothed_image  = cv2.GaussianBlur(source-image, ksize, sigmaX)


  • source-image:  Our input image
  • ksize: Gaussian kernel size. kernel width and height can differ but they both must be positive and odd. 
  • sigmaX: Gaussian kernel standard deviation in X direction.

Again to keep this short, I won’t be getting into the math nor the parameter details for how this function works, although it’s really interesting. One thing you need to learn is that by controlling the kernel size you control the level of smoothing done. There is also a SigmaX and a SigmaY parameter that you can control.


Thresholding an Image:

For this section, we will be using this image.

There are times when we need a binary black & white mask of the image, where our target object is in white and the background black or vice versa. The easiest way to get a mask of our image is to threshold our image. There are different types of thresholding methods, I’ve introduced most of them in our Computer Vision course but for now, we are going to discuss the most basic and most used one. So what thresholding does is that it checks each pixel in the image against a threshold value and If the pixel value is smaller than the threshold value, it is set to 0, otherwise, it is set to the maximum value, (this maximum value is usually 255 so white color).

ret, thresholded_image = cv2.threshold(source_image, thresh, max_value, type)


  • Source_image: This is your input image.
  • thresh: Threshold value. (If you use THRESH_BINARY then all values above this are set to max_value.)
  • max_value: Maximum value, normally this is set to be 255.
  • type: Thresholding type. The most common types are THRESH_BINARY  & THRESH_BINARY_INV
  • ret: Boolean variable which tells us if thresholding was successful or not.

Now before you can threshold an image you need to convert the image into grayscale, now you could have loaded the image in grayscale but since we have a color image already we can convert to grayscale using cv2.cvtColor function. This function can be used to convert one color to different color formats for this post we are only concerned with the grayscale conversion.


Now that we have a grayscale image, we can apply our threshold.

Line 2: We are applying a threshold such that all pixels having an intensity above 220 are converted to 255 and all pixels below 220 become 0.


Now Let’s see the result of the inverted threshold, which just reverses the results above. For this you just need to pass in cv2.THRESH_BINARY_INV instead of cv2.THRESH_BINARY.


Edge Detection:

Now we will take a look at edge detection, why edge detection? Well edges encode the structure of the images and it encodes most of the information in the images so for this reason edge detection is an integral part of many Vision applications.

In OpenCV there are edge detectors such as Sobel filters and laplacian filters but the most effective is the Canny Edge detector. In our Computer Vision Course I go into detail of exactly how this detector works but for now let’s take a look at its implementation in OpenCV.

edges = cv2.Canny( image, threshold1, threshold2)


  • image: This is our input image.
  • edges: output edge map; single channels 8-bit image, which has the same size as image .
  • threshold1: First threshold for the hysteresis procedure.
  • threshold2: Second threshold for the hysteresis procedure.

Line 1-2: I’m detecting edges with lower and upper hysteresis values being 30 and 150. I can’t explain how these values work without going into the theory so, for now, understand that for any image you need to tune these 2 threshold values to get the correct results.


Contour Detection:

Contour detection is one of my most favorite topics because with just contour detection you can do a lot and I’ve built a number of cool applications using contours.

Contours can be defined simply as a curve joining all the continuous points (along the boundary), having the same color or intensity. In simple terms think of contours as white blobs on black background for e.g. in the output of threshold function or the edge detection function, each shape can be considered as an individual contour. So you can segment each shape, localize them or even recognize them.

The contours are a useful tool for shape analysis, object detection, and recognition, take a look at this detection and recognition application I’ve built using contour detection.

You can use this function to detect contours.

contours, hierarchy = cv2.findContours(image, mode, method[, offset])


  • image Source: This is your input image in binary format, this is either a black & white image obtained from a thresholding or a similar function or the output of a canny edge detector.
  • mode: Contour retrieval mode, for example  cv2.RETR_EXTERNAL mode lets you extract only external contours meaning if there is a contour inside a contour then that child contour will be ignored. You can see other RetrievalModes here
  • method: Contour approximation method, for most cases cv2.CHAIN_APPROX_NONE works just fine.

After you detect contours you can draw them on the image by using this function.

cv2.drawContours( image, contours, contourIdx, color, [thickness] )


  • image: original input image.
  • contours: This is a list of contours, each contour is stored as a vector.
  • contourIdx: Parameter indicating which contour to draw. If it is -1 then all the contours are drawn.
  • color: Color of the contours.

Line 7 Using an Inverted threshold as the shapes need to be white and background black.

Line 10: Detecting contours on the thresholded image and drawing it on the image copy.

Line 13: Draw detected Contours.


You can also get the number of objects or shapes present by counting the number of contours.


Total Shapes present in image are: 6

Since there are 6 shapes in the above image we are seeing 6 detected contours.

Like I said with contours you can build some really amazing things, In our Computer Vision course, I’ve discussed contours in a lot of depth and also created several steps by step applications with it. For e.g. take a look at this Virtual Pen & Eraser post that I created on LearnOpencv.

Morphological Operations:

In this section, we will take a look at morphological operations. This is one of the most used preprocessing techniques to get rid of noise in binary (black & white) masks. They need two inputs, one is our input image and a kernel (also called a structuring element) which decides the nature of the operation. Two very common morphological operations are Erosion and Dilation. Then there are other variants like Opening, Closing, Gradient, etc.

In this post, we will only be looking at Erosion & Dilation. These are all you need in most cases.


The fundamental idea of erosion is just like how it sounds, it erodes (eats away or eliminates) the boundaries of foreground objects (Always try to keep foreground in white). So what happens is that a kernel slides through the image. A pixel in the original image (either 1 or 0) will be considered 1 only if all the pixels under the kernel is 1, otherwise, it is eroded (made to zero).

Erosion decreases the thickness or size of the foreground object or you can simply say the white region of image decreases. It is useful for removing small white noises.

eroded_image = cv2.erode(source_image, kernel, [iterations] )


  • source_image: Input image.
  • kernel: Structuring element or filter used for erosion if None is passed then, a 3x3 rectangular structuring element is used. The bigger kernel you create the stronger the impact of erosion on the image.
  • iterations: Number of times erosion is applied, the larger the number, greater the effect. 

We will be using this image for erosion, Notice the white spots, with erosion we will attempt to remove this noise. 

Line 5: Making a 7x7 kernel, bigger the kernel the stronger the effect.

Line 8: Applying erosion with 2 iterations, the values for kernel and iterations should be tuned according to your own images.


As you can see the white noise is gone but there is a small problem, our object (person) has become thinner. We can easily fix this by applying dilation which is the opposite of erosion.


It is just the opposite of erosion. It increases the white region in the image or size of the foreground object increases. So essentially dilation expands the boundary of Objects. Normally, in cases like noise removal, erosion is followed by dilation. Because, erosion removes white noises, but it also shrinks our object like we have seen in our example. So now we dilate it. Since noise is gone, they won’t come back, but our object area increases.

Dilation is also useful for removing black noise or in other words black holes in our object. So it helps in joining broken parts of an object.

dilated_image  = cv2.dilate( source_image, kernel, [iterations])

The parameters are the same as erosion.

We will attempt to fill up holes/gaps in this image.


computer vision

See the black holes/gaps are gone. You will find a combination of erosion and dilation used across many image processing applications.

Working with Videos:

We have learned how to deal with images in OpenCV, now let’s work with Videos in OpenCV. First, it should be clear to you that any operation you perform on images can be done on videos too since a video is nothing but a series of images, for e.g. Consider a 30 FPS video, which means this video shows 30 Frames (images) each second.

There are multiple ways to work with images in OpenCV, you first you have to initialize the camera Object by doing this:

cap = cv2.VideoCapture(arg)

Now there are 4 ways we can use the videoCapture Object depending what you pass in as arg:

1. Using Live camera feed: You pass in an integer number i.e. 0,1,2 etc e.g. cap = cv2.VideoCapture(0), now you will be able to use your webcam live stream.

2. Playing a saved Video on Disk: You pass in the path to the video file e.g. cap = cv2.VideoCapture(Path_To_video).

3. Live Streaming from URL using Ip camera or similar: You can stream from a URL e.g. cap = cv2.VideoCapture(protocol://host:port/script_name?script_params|auth) Note, that each video stream or IP camera feed has its own URL scheme.

4. Read a sequence of Images: You can also read sequences of images but this is not used much.

The next step After Initializing is read from video frame by frame, we do this by using

ret, frame =

  • ret:: A boolean variable which either returns True if the frame was successfully read otherwise False if it fails to read the next frame, this is a really important param when working with videos since after reading the last frame from the video this parameter will return false meaning it can’t read the next frame so we know we can exit the program now.
  • frame: This will be a frame/image of our video. Now everytime we run it will give us a new frame so we will put in a loop and show all the frames sequentially , it will look like we are playing a video but actually we are just displaying frame by frame.

After exiting the loop there is one last thing you must do, you must release the cap object you created by doing cap.release() otherwise your camera will stay on even after the program ends. You may also want to destroy any remaining windows after the loop.

Line 2: Initializing the VideoCapture object, if you’re using a usb cam then this value can be 1, 2 etc instead of 0

Line 6-17: looping and reading frame by frame from the camera, making sure it’s not corrupted and then converting to grayscale.

Line 24-25:  Check if the user presses the q under 1 millisecond after the imshow function, if yes then exit the loop. The ord() method converts a character to its ASCII value so we can compare it with the returned ASCII value of waitKey() method.

Line 28: Release the camera otherwise your cameras will be left on and the program will exit, this will cause problems the next time you run this cell.

Face Detection with Machine Learning:

In this section we will work with a machine learning-based face detection model, the model we are going to use is a Haar cascade based face detector. It’s the oldest known face detection technique that is still used today at some capacity, although there are more effective approaches, for e.g. take a look at Bleedfacedetector, a python library that I built a year back. It lets users use 4 different types of face detectors by just changing a single line of code.

This Haar Classifier has been trained on several positive (images with faces) and negative (images without faces) images. After training it has learned to recognize faces. 

Before using the face detector, you first must initialize it.


  • xml_model_file: This is your trained haar cascade model in a .xml file

Detected_faces = cv2.CascadeClassifier.detectMultiScale( image, [ scaleFactor], [minNeighbors])


  • Image: This is your input image.
  • scaleFactor: Parameter specifying how much the image size is reduced at each pyramid scale.
  • minNeighbors: Parameter specifying how many neighbors each candidate rectangle should have to retain it.

I’m not going to go into the details of this classifier so you can ignore the definitions of scaleFactor & minNeighbors and just remember that you should tune the value of scaleFactor for controlling speed/accuracy tradeoff. Also increase the number of minNeihbors if you’re getting lots of false detections. There is also a minSize & a maxSize parameter which I’m not discussing for now.

Let’s detect all the faces in this image.

computer vision