Housam Khalifa bashier1,2, Eimad Eldin Abdu Abusham 1,2, Fatimah Khalid 1,2
(1 Faculty of Computer Science and Information Technology, University Putra Malaysia, 43400 UPM Serdang , Selangor Darul Ehsan, Malaysia 2 Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia)
Abstract-The problem associated with Illumination variation is one of the major problems in image processing, pattern recognition, medical image, etc; hence there is a need to handle and deal with such variations. This paper presents a novel and efficient algorithm for face recognition call Housam-Eimad (H-E) features are derived from a general definition of texture of graph neighborhood. The experiments results on our face database images demonstrated the effectiveness of the proposed method. The new method can be stabilized more quickly and obtain higher correct rate. Finally, H-E is simple and can be easily applied in many fields, such as image processing, pattern recognition, medical image as pre-processing.
Key words-local graph structure; image processing; pattern recognition; Illumination variation; local binary pattern
Manuscript Number: 1674-8042(2011)supp1.-0069-05
doi: 10.3969/j.issn.1674-8042.2011.supp1.015
References
[1]Phillips P J, Grother P, Michaels R, et al. Facial Recognition Vendor Test 2002: Evaluation report, 2003.
[2]Gross R, Shi J, Cohn J. Quo vadis face recognition? Third Workshop on Empirical Evaluation Methods in Computer Vision, 2001.
[3]Gross R, Baker S, Matthews I, et al. Face recognition across pose and illumination, Chapter 9, Handbook of Face Recognition, Stan Z. Li and Anil K. Jain (Eds.), Springer-Verlag, 2004.
[4]Shin D, Lee H-S, kim D. Illumination-robust face recognition using ridge regressive bilinear models. Pattern Recognition Letters, 2008, 29: 49-58.
[5]Adini, Moses Y, Ullman S. Face recognition: the problem of compensating for changes in illumination direction (Report No. CS93-21). The Weizmann Institute of Science, 1995.
[6]Ruiz-del-Solar J, Quinteros J. Illumination Compensation and Normalization in Eigenspace-based Face Recognition: A comparative study of different pre-processing approaches. Pattern Recognition Letters, 2008, 29(14):1966-1979.
[7]Chui C K, An Introduction to Wavelets. Academic Press, Boston, 1992.
[8]Liu D, Lam K M, Shen L S. Optimal sampling of Gabor features for face recognition. Pattern Recognition Lett., 2004, 25 (2):267-276.
[9]Ojala T, Pietikinen M, Harwood D. A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, 1996, 29.
[10]Ojala T, Pietikinen M, Menp T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.
[11]Du S, Ward R. Wavelet-based illumination normalization for face recognition. Proceedings. of IEEE International Conference on Image Processing, 2005, 2: 954- 957.
[12]Pang Y, Yuan Y, Li X. Gabor-based region covariance matrices for face recognition. IEEE Trans. Circuits & Systems for Video Technology, 2008, 18(7): 989-993.
[13]Wiskott L, Fellous J-M, Kruger N, et al. Face recognition by elastic bunch graph matching. IEEE TPAMI, 1997, 19(7):775-779.
[full text view]
