Face Geometry and Appearance Modeling: Concepts and Applications

Description

Human faces are familiar to our visual systems. We easily recognize a person's face in arbitrary lighting conditions and in a variety of poses; detect small appearance changes; and notice subtle expression details. Can computer vision systems process face images as well as human vision systems can? Face image processing has potential applications in surveillance, image and video search, social networking and other domains. A comprehensive guide to this fascinating topic, this book provides a systematic description of modeling face geometry and appearance from images, including information on mathematical tools, physical concepts, image processing and computer vision techniques, and concrete prototype systems. The book will be an excellent reference for researchers and graduate students in computer vision, computer graphics and multimedia, as well as application developers who would like to gain a better understanding of the state of the art.

Dr Zicheng Liu is a Senior Researcher at Microsoft Research, Redmond. He has worked on a variety of topics including combinatorial optimization, linked figure animation and microphone array signal processing. His current research interests include activity recognition, face modeling and animation, and multimedia collaboration. He has published more than 70 papers in peer-reviewed international journals and conferences and holds more than 40 granted patents. Dr Zhengyou Zhang is a Principal Researcher with Microsoft Research, Redmond, and manages the multimodal collaboration research team. He has published more than 200 papers in refereed international journals and conferences and coauthored 3-D Dynamic Scene Analysis: A Stereo Based Approach (1992); Epipolar Geometry in Stereo, Motion and Object Recognition (1996); and Computer Vision (1998). He is an IEEE Fellow.

"The human face has fascinated people since time immemorial and many scientists would agree that, aside from the brain itself, the face is the most intriguing part of the human body. Attempting to emulate its form and function by computer is an extremely challenging problem because people are very sensitive to even the smallest shortcomings and defects in facial models. Liu and Zhang boldly tackle the difficult challenge of modeling the form and appearance of the face. The value of their book is enhanced tremendously by the fact that it not only presents and discusses their own work in detail, but also that delves into the technical details of a plethora of related methodologies and algorithms contributed by other researchers. I am pleased to highly recommend Zicheng Liu and Zhengyou Zhang's magnum opus to anyone interested in graphics and vision in general and the human face in particular. Let's face it, for people like us this book is an essential read." Demetri Terzopoulos, The Chancellor's Professor of Computer Science, University of California, Los Angeles "Whether you are developing facial representations, modeling appearance, working with applications, or surveying the subject, this book is likely to have something for you and is a good resource to have on hand." Alyx Macfadyen, Computing Reviews