Book Image

Mastering OpenCV 3 - Second Edition

By : Jason Saragih
Book Image

Mastering OpenCV 3 - Second Edition

By: Jason Saragih

Overview of this book

As we become more capable of handling data in every kind, we are becoming more reliant on visual input and what we can do with those self-driving cars, face recognition, and even augmented reality applications and games. This is all powered by Computer Vision. This book will put you straight to work in creating powerful and unique computer vision applications. Each chapter is structured around a central project and deep dives into an important aspect of OpenCV such as facial recognition, image target tracking, making augmented reality applications, the 3D visualization framework, and machine learning. You’ll learn how to make AI that can remember and use neural networks to help your applications learn. By the end of the book, you will have created various working prototypes with the projects in the book and will be well versed with the new features of OpenCV3.
Table of Contents (14 chapters)
Title Page
Mastering OpenCV 3 Second Edition
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface

Overview


Non-rigid face tracking was first popularized in the early to mid-1990s with the advent of Active Shape Models (ASM) by Cootes and Taylor. Since then, a tremendous amount of research has been dedicated to solving the difficult problem of generic face tracking with many improvements over the original method that ASM proposed. The first milestone was the extension of ASM to Active Appearance Models (AAM) in 2001, also by Cootes and Taylor. This approach was later formalized though the principled treatment of image warps by Baker and colleges in the mid-2000s. Another strand of work along these lines was the 3D morphable model (3DMM) by Blanz and Vetter, which like AAM, not only modeled image textures as opposed to profiles along object boundaries as in ASM, but took it one step further by representing the models with a highly dense 3D data learned from laser scans of faces. From the mid- to late 2000s, the focus of research on face tracking shifted away from how the face was parameterized...