(28) * << * >> * Russian * English * Content * All Issues
Development of face recognition classifiers based on contingency indicators
N.E. Kozin1,2 V.A. Fursov1,2
1Image Processing Systems Institute of RAS
2Samara State Aerospace University named after academician S.P. Korolev
PDF, 119 kB
One of the most widely used face recognition techniques is the Principal Component Analysis (PCA), sometimes referred to as the Eigenfaces method. The idea of the method is to decompose the image vectors into a system of eigenvectors corresponding to the largest eigenvalues. The paper considers to use as a proximity measure various coefficients of contingency with a subspace spanned by training vectors from a recognizable class. The effectiveness of using this criterion in case of a small number of training examples is shown. Experimental results for the standard ORL face database are provided.
face recognition, contingency indicator, principal component analysis, PCA, eigenfaces, ORL face database.
Kozin NE, Fursov VA. Development of face recognition classifiers based on contingency indicators. Computer Optics 2005; 28: 160-163.
- Zhao W, Chellappa R, Rosenfeld A, Phillips PJ. Face recognition: A literature survey. ACM Comput Surv 2003; 35(4): 399-458.
- Turk MA, Pentland AP. Face recognition using eigenfaces. Proc IEEE Conf on Computer Vision and Pattern Recognition 1991: 586-591.
- Belhumeur PN, Hespanha JP, Kriegman DJ. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. Proc 4th European Conference on Computer Vision ECCV'96 1996: 45-58.
- Fursov VA, Kozin NE. Stage-wise learning of radial neural networks. Next Generation Concurrent Engineering: Smart and Concurrent Integration of Product Data, Services, and Control Strategies (CE 2005) 2005: 391-395.
- Fursov VA, Kozin NE. Algorithm for parallel learning of radial neural networks. Proc IASTED International Conference on Automation, Control and Applications (ACIT-ACA 2005) 2005: 481-485.
- Turk A, Pentland AP. Face recognition using eigenfaces. Proc IEEE Conf on Computer Vision and Pattern Recognition 1991: 586-591.
- Berger M, Sobolewski M. SILENUS – A federated service-oriented approach to distributed file systems. In Book: Sobolewski M, Ghodous P, eds. Smart and Concurrent Integration of Product Data, Services, and Control Strategies 2005: 89-96.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: firstname.lastname@example.org ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20