| Face recognition has been actively studied over the past decade and continues to be a big research challenge. Just recently, researchers have begun to investigate face recognition under unconstrained conditions. Unconstrained Face Recognition provides a comprehensive review of this biometric, especially face recognition from video, assembling a collection of novel approaches that are able to recognize human faces under various unconstrained situations. The underlying basis of these approaches is that, unlike conventional face recognition algorithms, they exploit the inherent characteristics of the unconstrained situation and thus improve the recognition performance when compared with conventional algorithms. Unconstrained Face Recognition is structured to meet the needs of a professional audience of researchers and practitioners in industry. This volume is also suitable for advanced-level students in computer science.
Although face recognition has been actively studied over the past decade, the state-of-the-art recognition systems yield satisfactory performance only under controlled scenarios and recognition systems degrade significantly when confronted with unconstrained situations.
Examples of unconstrained conditions include illumination and pose variations, video sequences, expressions, aging, and so on. Recently, researchers have begun to investigate face recognition under unconstrained conditions. For example, as video sequence becomes ubiquitous due to advances in digital imaging devices and the advent of the Internet era, face recognition based on video sequences is gaining more attention. Face recognition under illumination and pose variations remains a big challenge to researchers.
The goal of this book is to provide a comprehensive review of unconstrained face recognition, especially face recognition from video, and to assemble descriptions of novel approaches that are able to recognize human faces under various unconstrained situations. The underlying theme of these approaches is that, unlike conventional face recognition algorithms, they exploit the inherent characteristics of the unconstrained situation and gain improvements in recognition performance when compared with conventional algorithms. For instance, generalized photometric stereo combines physics-based illumination model with statistical modeling to address face recognition under illumination variation. Simultaneous tracking and recognition employs the temporal information embedded in a video sequence and thus improves both tracking accuracy and recognition performance. |
