Preface

Computer vision is one of the most widely studied sub-fields of computer science. It has several important applications, such as face detection, image searching, and artistic image conversion. With the popularity of deep learning methods, many recent applications of computer vision are in self-driving cars, robotics, medicine, Virtual reality, and Augmented reality. In this book, a practical approach of learning computer vision is shown. Using code blocks as well as a theoretical understanding of algorithms will help in building stronger computer vision fundamentals. This book teaches you how to create applications using standard tools such as OpenCV, Keras, and TensorFlow. The various concepts and implementations explained in this book can be used across several domains, such as robotics, image editing apps, and self-driving cars. In this book, each chapter is explained with accompanying code and results to enforce the learning together.