Book Image

The Computer Vision Workshop

By : Hafsa Asad, Vishwesh Ravi Shrimali, Nikhil Singh
Book Image

The Computer Vision Workshop

By: Hafsa Asad, Vishwesh Ravi Shrimali, Nikhil Singh

Overview of this book

Computer Vision (CV) has become an important aspect of AI technology. From driverless cars to medical diagnostics and monitoring the health of crops to fraud detection in banking, computer vision is used across all domains to automate tasks. The Computer Vision Workshop will help you understand how computers master the art of processing digital images and videos to mimic human activities. Starting with an introduction to the OpenCV library, you'll learn how to write your first script using basic image processing operations. You'll then get to grips with essential image and video processing techniques such as histograms, contours, and face processing. As you progress, you'll become familiar with advanced computer vision and deep learning concepts, such as object detection, tracking, and recognition, and finally shift your focus from 2D to 3D visualization. This CV course will enable you to experiment with camera calibration and explore both passive and active canonical 3D reconstruction methods. By the end of this book, you'll have developed the practical skills necessary for building powerful applications to solve computer vision problems.
Table of Contents (10 chapters)

Introduction to Haar Cascades

Before we jump into understanding what Haar Cascades are, let's try to understand how we would go about detecting faces. The brute-force method would be to have a window or a block that will slide over the input image, detecting whether there is a face present in that region or not. Detecting whether the block is a face or not can be done by comparing it with some sample face image. Let's see what the issue is with this approach.

The following is a picture of a group of people:

Figure 5.1: Picture of a group of people

Notice the variety of faces in this image. Now, let's look at the following self-explanatory representation of the brute-force method for face detection:

Figure 5.2: Brute-force method for face detection

Here, we can see how difficult it would be if we were to create one standard face that can be used as a reference face to check whether a region in an image has a face or...