Face recognition under varying views

In this paper "EIGENFACES" are used to recognize human faces. We have developed a method that uses three eigenspaces. The system can identify faces under different angles, even if considerable changes were made in the orientation. First of all we represent the face using the Karhunen-Loeve transform. The face entered is automatically classified according to its orientation. Then we applied the rule of decision of the minimal distance for the identification. The system is simple, powerful and robust.

[1]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[3]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[4]  Ingemar J. Cox,et al.  Feature-based face recognition using mixture-distance , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Takeo Kanade,et al.  Picture Processing System by Computer Complex and Recognition of Human Faces , 1974 .

[7]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.