Evolutionary Eigenspace Learning using CCIPCA and IPCA for Face Recognition

Authors: Ghazy M.R. Assassa, Mona F. M. Mursi, Hatim A. Aboalsamh

Abstract:

Traditional principal components analysis (PCA) techniques for face recognition are based on batch-mode training using a pre-available image set. Real world applications require that the training set be dynamic of evolving nature where within the framework of continuous learning, new training images are continuously added to the original set; this would trigger a costly continuous re-computation of the eigen space representation via repeating an entire batch-based training that includes the old and new images. Incremental PCA methods allow adding new images and updating the PCA representation. In this paper, two incremental PCA approaches, CCIPCA and IPCA, are examined and compared. Besides, different learning and testing strategies are proposed and applied to the two algorithms. The results suggest that batch PCA is inferior to both incremental approaches, and that all CCIPCAs are practically equivalent.

Keywords: Candid covariance-free incremental principal components analysis (CCIPCA), face recognition, incremental principal components analysis (IPCA).

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1078767

References:

[1] J. Haddadnia, K. Faez, and A. Majid, "N-Feature Neural Network Human Face Recognition," Image Vision Computing 22, pp. 1071-1082, 2004.
[2] B.L. Zahng, H. Zhang, and S.S. Ge, "Face Recognition by Applying Wavelet Subband Representation and Kernel Associative Memory," IEEE Trans. Neural Networks, vol. 15, no. 1, pp. 166-177, Jan. 2004.
[3] A. F. Abate, M. Nappi, D. Riccio, and G. Sabatino, "2D and 3D Face Recognition: A Survey," Pattern Recognition Letters, 28, pp. 1885-1906, 2007.
[4] W. Zhao and R. Chellappa, ed, Face Processing: Advanced Modeling and Methods, Academic Press, Elsevier Inc, 2006.
[5] A. Eleyan and H. Demirel, "PCA and LDA based Neural Networks for Human Face Recognition," Face Recognition, edited by Kresimir Delac and Mislav Grgic, p. 558, I-Tech, Vienna, Austria, June 2007.
[6] K-C. Kwak and W. Pedryez, "Face Recognition: A Study in Information Fusion using Fuzzy Intrgral," Pattern recognition Letters, vol. 26, pp. 719-733, 2005.
[7] M. Turk, and A. Pentland, "Ejgenfaces for Recognition," Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[8] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, "Eigenfaces vs. Fisherfaces: RecognitionUsing Class Specific Linear Projection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, 1997.
[9] M.S. Bartlett, J.R. Movellan, and T.J. Sejnowski, "Face Recognition by Independent Components Analysis," IEEE trans. Neural Networks, vol. 13, no. 6, pp.1450-1464, 2002.
[10] H. Shum, K. Ikeuchi, and R. Reddy, "Principal component analysis with missing data and its application to polyhedral object modeling," PAMI, 17(9):854-867, 1995.
[11] H. Sidenbladh, F. de la Torre, and M. J. Black, "A framework for modeling the appearance of 3D articulated figures," in AFGR00, pages 368-375, 2000.
[12] F. De la Torre and M. J. Black, "Robust principal component analysis for computer vision," in ICCV-01, I: 362-369, 2001.
[13] K. Gabriel and S. Zamir, "Lower rank approximation of matrices by least squares with any choice of weights," Technometrics, 21(21):489- 498, 1979.
[14] H. A. Aboalsamh, "Human Face Recognition using Eigen and Fisher Faces," Egyptian Computer Science Journal, vol. 31, no. 1, (accepted), January 2009.
[15] S. Chandrasekaran, B. S. Manjunath, Y. F.Wang, J.Winkeler, and H. Zhang, "An eigenspace update algorithm for image analysis," Graphical Models and Image Processing, 59(5):321-332, September 1997.
[16] P. Hall, D. Marshall, and R. Martin, "Incremental eigenanalysis for classification," in British Machine Vision Conference, volume 1, pages 286-295, September 1998.
[17] P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," PAMI, 22(9):1042-1048, 2000.
[18] D. Skoˇcaj and A. Leonardis, "Weighted and Robust Incremental Method for Subspace Learning," Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV-03), 2003.
[19] A. Levy and M. Lindenbaum, "Sequential karhunen-loeve basis extraction and its application to images," IEEE Trans. On Image Processing, 9:1371-1374, June 2000.
[20] X. Liu and T. Chen, "Shot boundary detection using temporal statistics modeling," in ICASSP 2002, May 2002.
[21] S. Ozawa, S.L Toh, S. Abe, Shaoning Pang, and N. Kasabov, "Incremental learning for online face recognition," Proceedings of the IEEE International Joint Conference on Neural Networks, IJCNN, 2005.
[22] H. Zhao, P.C. Yuen, and J.T. Kwok, "A Novel Incremental Principal Component Analysis and Its Application for Face Recognition," IEEE Transactions On Systems, Man, And CyberneticsÔÇöPart B: Cybernetics, vol. 36, no. 4, pp. 873-886 August 2006.
[23] J. Weng, Y. Zhang, and W. S. Hwang, "Candid covariance-free incremental principal component analysis," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 8, pp. 1034-1040, Aug. 2003.
[24] T. D. Sanger, "Optimal unsupervised learning in a single-layer linear feed forward neural network," Neural Netw., vol. 2, pp. 459-473, 1989.
[25] E. Oja and J. Karhunen, "On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix," J. Math. Anal. Appl., vol. 106, no. 1, pp. 69-84, 1985.
[26] H. A. Aboalsamh, H. Mathkour, G. M.R. Assassa. And M F. Mursi, "Face Recognition using Incremental Principal Components Analysis," International Conference on Computing in Engineering Science and Information, ICC 2009, University of California, Fullerton, April 2009, (accepted).