Composite support vector machines for detection of faces across views and pose estimation

Support vector machines (SVMs) have shown great potential for learning classi®cation functions that can be applied to object recognition. In this work, we extend SVMs to model the appearance of human faces which undergo non-linear change across multiple views. The approach uses inherent factors in the nature of the input images and the SVM classi®cation algorithm to perform both multi-view face detection and pose estimation. q 2002 Published by Elsevier Science B.V.