Intelligent Face Recognition: Local Versus Global Pattern Averaging
Face recognition has lately attracted more research aimed at developing intelligent machine recognition which uses information within the encoded facial patterns to learn and recognize the objects. This paper investigates the efficiency of using Global and Local pattern averaging for facial data encoding prior to training a neural network using the averaged patterns. Averaging is a simple but efficient method that creates "fuzzy" patterns as compared to multiple "crisp" patterns, which provide the neural network with meaningful learning while reducing computational expense. A real-life application will be presented throughout recognizing the faces of 60 persons using our database and the ORL face database. Experimental results suggest that using pattern averaging; globally or locally, performs well as part of a fast and efficient intelligent face recognition system.
KeywordsNeural Network Face Recognition Recognition Rate Face Image Local Average
Unable to display preview. Download preview PDF.
- 2.Fan, X., Verma, B.: A Comparative Experimental Analysis of Separate and Combined Facial Features for GA-ANN based Technique. In: Proceedings of International Conference on Computational Intelligence and Multimedia Applications, pp. 279–284 (2005)Google Scholar
- 5.Turk, M., Pentland, A.P.: Face Recognition Using Eigenfaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–591 (1991)Google Scholar
- 6.Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Trans. PAMI 19(7), 711–720 (1997)Google Scholar
- 7.He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.J.: Face Recognition Using Laplacianfaces. IEEE Trans. PAMI 27(3), 328–340 (2005)Google Scholar
- 8.Cambridge University, Olivetti Research Laboratory face database, http://www.uk.research.att.com/facedatabase.html