The fundamental principles of computer vision based on image processing technologies are presented in this book. The style of the content is informal; meanwhile, a lot of equations are involved. The reader should have enough math background, including linear algebra, optimization (function minimization), probability, and so on, before jumping into this book.
The book is divided into 13 chapters. Chapter 1 provides a basic overview of computer vision and some definitions in the field. Chapter 2 discusses programming for image processing. Chapter 3 presents a review of mathematical principles. Chapter 4 examines image representation in different forms. Chapter 5 presents kernel operators. Chapter 6 focuses on noise removal. Chapter 7 discusses mathematical morphology. Chapter 8 focuses on segmentation, including k-means, active contours (snake and level sets), graph cuts, and so on. In chapter 9, the book moves on to parametric transforms. Chapters 10 and 11 focus on representing and matching shapes and scenes. Chapter 12 talks about 3D-related technologies like camera geometry, shape from motion, and so on. The last chapter (13) gives a summary of how to develop computer vision algorithms.
The presented principles and ideas are extensive and refreshing. The book also includes state-of-the-art methods, so it is great for those who want to have a complete picture of what computer vision is about, what has been done, and how it develops in the field.
The book provides wide content and analysis of computer vision methods, including math deductions and algorithms (for example, k-means clustering). As the preface states: “This book introduces the fundamental principles of computer vision to the advanced undergraduate or first-year graduate student in mathematics, computer science, or engineering.” This is a great book for graduate students pursuing a PhD and computer vision researchers.
More reviews about this item: Goodreads