This paper aims to present face recognition based on Principal Component Analysis (PCA) and Modular Principal Component Analysis (MPCA) approach. The PCA based face recognition method is not very effective under the conditions of varying poses and expressions rather than the proposed MPCA method. In the MPCA method the original face image was partitioned into tiny sub-images and then PCA technique is applied for each sub-image. Since a few of the normal facial features of an individual do not differ even when the pose and expression may differ, the proposed method manages these variations and takes only a few numbers of principal components for matching the faces for similarity. The proposed method improves the recognition rates with less number of principal components when compared with the conventional PCA method. This present system is tested with two standard face databases and results are presented.

Eigen faces; Euclidean Distance; Face Recognition; MPCA; Principal Component Analysis

[1] Muge Carikci, Figen Ozen, “A face recognition method based on eigenface method”, Prcedia Techonology 1 (2012) 118-123.
[2] H. Wang, S. Chen, Z. Hu, B. Luo , “Probabilistic two-dimensional principal component analysis and its mixture model for face recognition”, Neural Comput & Applic (2008) 17: 541-547
[3] M. Turk, A. Pentland, “Eigenfaces for recognition”, J. Cognitive Neurosci. 3 (1) (1991) 71-85
[4] M. Turk, A. Pentland, “Face recognition using eigenfaces”, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 1991, pp. 586-591
[5] P.N Belhumeur, J. P. Hespanha, and D. J. Kriegman, “ Eigenfaces vs Fisherfaces:Recognition using class specific linear projection”, IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 711-720, Jul. 1997.
[6] R.O.Duda, P. E. Hart, and D. G. Stork,” Pattern classification”, 2nd ed.. USA: John Wiley & Sons, 2001.
[7] L. Sirovich , M. Kirby, “Low-Dimensional Procedure for Characterization of Human Faces,” J. Optical Soc. Am., vol. 4, pp. 519-524, 1987.
[8] M. Kirby, L. Sirovich, “Application of the KL Procedure for the Characterization of Human Faces”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, Jan. 1990.
[9] S.Chen, Y.Zhu, “Subpattern-based principal component analysis”, Pattern Recognition 37 (2004) 1081-1083.
[10] K. Tan, S.Chen, “Adaptively weighted sub-pattern PCA for face recognition”, Neurocomputing 64 (2005) 505-511.
[11] Hussein Rady, “Face recognition using Principle Component Analysis with different distance classifiers”, International Journal of Computer Science and Network Security, Volume 11, No.10, October 2011.
[12] Minkook Cho, Hyeyoung Park,” A feature analysis for dimension reduction based on a data generation model with class factors and environment factors”, Computer Vision and Image Understanding, 113 (2009) 1005-1016.
[13] R. Gottumukkal, V. K. Asari,” An improved face recognition technique based on modular PCA approach”, Pattern Recognition Lett. 25 (4) (2004) 429-436.
[14] Rajesh Kumar Gupta, Umesh Kumar Sahu,” Real time face recognition under different conditions”, International Journal of Advance Research in Computer Science and Software Engineeirng, Volume 3,Issue 1, January 2013.
[15] Jie Wang, K. N. Plataniotis, A. N. “Venetsanopoluos, Select discriminant for face recognition”, Pattern Recognition Letters 26 (2005) 1470-1482.
[16] Xiaoyang Tan, Bill Triggs, “Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions”, IEEE Transactions on Image Processing, Vol. 19, No .6, June 2010.
[17] Javier Ruiz-del-Solar, Pablo Navarrete, “Eigenspace – Based Face Recognition: A Comparative Study of Different Approches”, IEEE Transcations On Systems, Man, And Cybernetics – PART C: Applications and Reviews, Vol., 35, No. 3, August 2005.
[18]http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
[19]http://see.xidian.edu.cn/vipsl/database_Face.html#UMIST