Book Image

Mastering Computer Vision with TensorFlow 2.x

By : Krishnendu Kar
Book Image

Mastering Computer Vision with TensorFlow 2.x

By: Krishnendu Kar

Overview of this book

Computer vision allows machines to gain human-level understanding to visualize, process, and analyze images and videos. This book focuses on using TensorFlow to help you learn advanced computer vision tasks such as image acquisition, processing, and analysis. You'll start with the key principles of computer vision and deep learning to build a solid foundation, before covering neural network architectures and understanding how they work rather than using them as a black box. Next, you'll explore architectures such as VGG, ResNet, Inception, R-CNN, SSD, YOLO, and MobileNet. As you advance, you'll learn to use visual search methods using transfer learning. You'll also cover advanced computer vision concepts such as semantic segmentation, image inpainting with GAN's, object tracking, video segmentation, and action recognition. Later, the book focuses on how machine learning and deep learning concepts can be used to perform tasks such as edge detection and face recognition. You'll then discover how to develop powerful neural network models on your PC and on various cloud platforms. Finally, you'll learn to perform model optimization methods to deploy models on edge devices for real-time inference. By the end of this book, you'll have a solid understanding of computer vision and be able to confidently develop models to automate tasks.
Table of Contents (18 chapters)
1
Section 1: Introduction to Computer Vision and Neural Networks
6
Section 2: Advanced Concepts of Computer Vision with TensorFlow
11
Section 3: Advanced Implementation of Computer Vision with TensorFlow
14
Section 4: TensorFlow Implementation at the Edge and on the Cloud

Semantic Segmentation and Neural Style Transfer

The application of a deep neural network is not only restricted to finding an object in an image (which we learned about in the previous chapters) it can also be used to segment images into spatial regions, thereby producing artificial images and transferring style from one image to another.

In this chapter, we will use TensorFlow Colab to perform all these tasks. Semantic segmentation predicts whether each pixel of an image belongs to a certain class. It is a useful technique for image overlaying. You will learn about TensorFlow DeepLab so that you can perform semantic segmentation on images. Deep Convolutional Generative Adversarial Networks (DCGANs) are powerful tools that are used to produce artificial images such as human faces and handwritten digits. They can also be used for image inpainting. We will also discuss...