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)

GrabCut Technique

Before we go into the details of this amazing technique, we need to understand the term Image Segmentation, which will form the very basis of GrabCut. In layman's terms, an image segmentation task comprises dividing the pixels into different categories based on the class they belong to. Here, the classes we are looking for are just the background and foreground. This means that we want to segment the image by deciding what region of the image is part of the background and what region of the image is part of the foreground.

Note

In deep learning, image segmentation is a very big topic and is comprised of segmenting an image based on its classes, sometimes based on semantics, and so on. For now, we can consider GrabCut a simple background removal technique, though technically it can also be considered as an image segmentation technique with only two primary classes in mind – background and foreground. It's also important to note here that GrabCut...