by Kazunori Okada (Author)
Automatic face recognition is one of the most fascinating and challenging problems in computer vision. It is important for understanding the human visual cognition and useful in various vision applications. A great difficulty in face recognition is the separation of intrinsic facial characteristics from extrinsic image variations such as pose, illumination, and expression. This book presents a novel approach for processing head pose information in 2D images for analysis, synthesis and identification tasks. A localized two-stage linear system and its piecewise linear extension are used to model the continuous change of head-pose in the facial shape and texture appearances. Successful handling of head pose variation is one of the key factors for realizing facial information processing systems in virtually any realistic and practical scenario. The main contribution of this study is a solution that is simultaneously simple, general, and accurate. Its data-driven nature allows for extending our solution to other types of variation and object. Possible applications include on-line sequential learning systems and human-computer interaction.