Comparing the performance of single-layer and two-layer support vector machines on face detection

Face detection is a vibrant research branch of computer vision. Methods of detecting faces fall into two categories: global and component-based. In this paper, we compare these two approaches by applying a single-layer and a dual-layer support vector machine classifier to detect faces from images. Experiments suggest that the single-layer classifier has better performance on detecting faces with big attitude extremity. But the dual-layer classifier has equivalent performance on detecting frontal faces and has more generality on different databases.

[1]  Terry Caelli,et al.  Learning Image Annotation : The CITE System , 1998 .

[2]  Andreas Christmann,et al.  Support Vector Machines , 2008, Data Mining and Knowledge Discovery Handbook.

[3]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Tomaso A. Poggio,et al.  Face recognition: component-based versus global approaches , 2003, Comput. Vis. Image Underst..

[5]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[6]  Luca Lombardi,et al.  Hierarchical architectures for computer vision , 1995, Proceedings Euromicro Workshop on Parallel and Distributed Processing.

[7]  Nikolas P. Galatsanos,et al.  Support vector machine learning for detection of microcalcifications in mammograms , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.

[8]  Thomas Serre,et al.  Categorization by Learning and Combining Object Parts , 2001, NIPS.

[9]  Volker Blanz,et al.  Face Recognition Using Component-Based SVM Classification and Morphable Models , 2002, SVM.

[10]  E Mjolsness,et al.  Machine learning for science: state of the art and future prospects. , 2001, Science.

[11]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[12]  Sven Behnke,et al.  Neural abstraction pyramid: a hierarchical image understanding architecture , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[13]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .