Get to know the algorithms that that enables computers to perceive
Table of Contents
The word computer vision means the ability of a computer to see and perceive the surrounding. A lot of application holds for computer vision to cover — Object detection and recognition, self driving cars, facial recognition, ball tracking, photo tagging, and many more. Before diving in the technical jargons, first let’s discuss the entire computer vision pipeline.
The entire pipeline is divided into 5 basic steps, each with a specific function. Firstly, the input is needed for the algorithm to process that can be in the form of an image or stream of image (image frames). The next step is pre-processing. In this step, functions are applied to the incoming image(s) so that the algorithm can better understand the image.
Some of the functions involve noise reduction, image scaling, dilation, and erosion, removing color spots, etc. The next step is selecting the area of interest or the region of interest. Under this lies the object detection and image segmentation algorithms. Further, we have feature extraction that means retrieving relevant information/features from the images that are necessary for accomplishing the end goal.
The final step is recognition or prediction, where we recognize objects in a given frame of images or predict the probability of the object in a given image frame.
Let’s look at a real world application of the computer vision pipeline. Facial expression recognition is an application of computer vision that is used by a lot of research labs to get an idea of what effect a particular product has on its users. Again, we have input data to which we apply the pre-processing algorithms.
The next step involves detecting faces in a particular frame and cropping that part of the frame. Once this is achieved, facial landmarks are identified like mouth, eyes, nose, etc. — key features for emotion recognition.
In the end, a prediction model( trained model) classifies the images based on the features extracted in the intermediary steps.
Before I start mentioning the algorithms in computer vision, I want to stress the term ‘Frequency’. The frequency of an image is the rate of change of intensity. High-frequency images have large changes in intensity. A low-frequency image is relatively uniform in brightness or the intensity changes slowly.
On applying Fourier transform to an image we get a magnitude spectrum that yields the information of the image frequency. Concentrated point in the center of the frequency domain image means a lot of low frequency components are present in the image. High frequency components include — edges, corners, stripes, etc. We know that an image is a function of x and y f(x,y). To measure the intensity change, we just take the derivative of the function f(x,y).
The Sobel operator is used in image processing and computer vision for edge detection algorithms. The filter creates an image of emphasizing edges. It computes an approximation of the slope/gradient of the image intensity function. At each pixel in the image, the output of the Sobel operator is both the corresponding gradient vector and the norm of this vector.
The Sobel Operator convolves the image with a small integer-valued filter in the horizontal and vertical directions. This makes the operator inexpensive in terms of computation complexity. The Sx filter detects edges in the horizontal direction and Sy filter detects edges in the vertical direction. It is a high pass filter.
Applying Sx to the image
Applying Sy to the image
Average filter is a normalized filter which is used to determine the brightness or darkness of an image. The average filter moves across the image pixel by pixel replacing each value in the pixel with the average value of the neighboring pixels, including itself.
The Average (or mean) filtering smoothens the images by reducing the amount of variation in the intensity between the neighboring pixels.
Average filter, Image source
Gaussian Blur Filter
Gaussian blur filter is a low pass filter and it has the following functions:
- Smooths an image
- Blocks high frequency parts of an image
- Preserves edges
Mathematically, by applying a Gaussian blur to an image we are basically convolving the image with a Gaussian function.
In the above formula, x is the horizontal distance from the point of origin, y is the vertical distance from the origin point, and σ is the standard deviation of the Gaussian distribution. In two dimension, the formula represents a surface whose profiles are concentric circles with a Gaussian distribution from the point of origin.
Gaussian Blur Filter, Image source
One thing to note here is the importance of choosing a right kernel size. It is important because if the kernel dimension is too large, small features present in the image may disappear and the image will look blurred. If it is too small, the noise in the image will not be eliminated.
Also Read: Types of AI Algorithm You Should Know
Canny Edge Detector
It is an algorithm that makes use of four filters to detect horizontal, vertical and diagonal edges in the blurred image. The algorithm performs the following functions.
- It is a widely used an accurate edge detection algorithm
- Filters out noise using Gaussian Blur
- Finds the strength and direction of edges using Sobel filter
- Applies non-max suppression to isolate the strongest edges and thin them to one pixel line
- Uses hysteresis(double thresholding method) to isolate the best edges
Canny Edge detector on a steam engine photo, Image by Wikipedia
This is a machine learning based approach where a cascade function is trained to solve binary classification problems. The function is trained from a plethora of positive and negative images and is further used to detect objects in other images. It detects the following:
- Rectangular patterns
To detect the above patterns, following features are used:
In this approach, the neural network learns the features of a group of images belonging to the same category. The learning takes place by updating the weights of the neurons using back propagation technique and gradient descent as an optimizer.
It is an iterative process that aims to decrease the error between the actual output and the ground truth. The convolution layers/blocks so obtained in the process act as feature layers that are used to distinguish a positive image from a negative one. Example of a convolution layer is given below.
Convolutional Neural Network, Image Source
The fully connected layers along with a SoftMax function at the end categorizes the incoming image into one of the categories it is trained on. The output score is a probabilistic score with a range between 0 to 1.
Must Read: Types of Classification Algorithm in ML
An overview of the most common algorithms used in Computer Vision has been covered in this blog along with a general pipeline. These algorithms form the basis of more complicated algorithms like SIFT, SURF, ORB, and many more.
If you’re interested to learn more about machine learning, check out IIIT-B & upGrad’s PG Diploma in Machine Learning & AI which is designed for working professionals and offers 450+ hours of rigorous training, 30+ case studies & assignments, IIIT-B Alumni status, 5+ practical hands-on capstone projects & job assistance with top firms.
What is the difference between Image Processing and Computer Vision?
Image Processing enhances the raw form of images to produce a better version. It is used for extracting some features of the primary image as well. Image Processing is hence a distinct section in the Computer Vision field itself. However, Computer Vision focuses on recognising stimuli objects for accurate classification. Both also use similar technologies in their procedure. Hence, Image Processing can be the primary process in Computer Vision. It remains to be a prominent field in Artificial Intelligence. Image Processing focuses on enhancing images; Computer Vision technology focuses on detailed, accurate analytics to create better systems.
Why is Deep Learning used to build Computer Vision algorithms?
Computer Vision has made Artificial Intelligence(AI) more robust due to rigorous data-driven research and consistent visual data analysis. Deep Learning is a continuous process of data input through neural networks. The information is derived from human brain processes to perfect the algorithm for efficient learning, processing, and output. Deep Learning enhances accurate data classification, ensures a reliable AI model. Computer Vision uses this method to align AI to the human brain’s neural network. Deep Learning has enabled dependable systems to assist humans and improve their quality of life.
What is a Low Pass filter and High Pass filter?
In Computer Vision Algorithms, multiple filters produce desired outcomes from a raw image. These filters perform numerous functions to smoothen, sharpen and accentuate the appearance as desired. The filters differ in their frequency and propose different effects. For e.g., The Gaussian Blur filter essentially works on smoothing the image by altering the high-frequency parts of the image and preserving the edges. It is called a Low Pass filter because it diminishes the high-frequency locations and maintains the low-frequency locations giving it a smoother visual. In High Pass filters, the low-frequency locations are decreased, and the former preserved, which results in a sharper visual.