Fusing Local Binary Patterns with Wavelet Features for Ethnicity Identification

Authors: S. Hma Salah, H. Du, N. Al-Jawad

Abstract:

Ethnicity identification of face images is of interest in many areas of application, but existing methods are few and limited. This paper presents a fusion scheme that uses block-based uniform local binary patterns and Haar wavelet transform to combine local and global features. In particular, the LL subband coefficients of the whole face are fused with the histograms of uniform local binary patterns from block partitions of the face. We applied the principal component analysis on the fused features and managed to reduce the dimensionality of the feature space from 536 down to around 15 without sacrificing too much accuracy. We have conducted a number of preliminary experiments using a collection of 746 subject face images. The test results show good accuracy and demonstrate the potential of fusing global and local features. The fusion approach is robust, making it easy to further improve the identification at both feature and score levels.

Keywords: Ethnicity identification, fusion, local binary patterns, wavelet.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1087015

References:

[1] Li, S. and Jain, A. K. editor. “Handbook of face recognition”, 2nd Ed. Springer London, 2011
[2] Gutta, S., Huang, J.R.J., Jonathon P., and Wechsler, H., “Mixture of experts for classification of gender, ethnic origin, and pose of human faces”, IEEE Transactions on Neural Networks, 2000, Vol.11, No.4, pp948-960
[3] Lu, X. and Jain, A.K., "Ethnicity identification from face images", Proceedings of SPIE International Symposium on Defense and Security: Biometric Technology for Human Identification, Orlando, Florida, April, 2004, pp.114--123
[4] Manesh, F.S., Ghahramani, M., and Tan, Y., "Facial part displacement effect on template-based gender and ethnicity classification", Control Automation Robotics & Vision (ICARCV), Proceedings of the 11th International Conference on Control, Automation, Robotics and Vision, Singapore, December, 2010, pp.1644-1649
[5] Duan, X. D., Wang, C. R., Liu, X. D., Li, Z. J., Wu, J., Zhang, H. L., "Ethnic features extraction and recognition of human faces", Proceedings of the 2nd International Conference on Advanced Computer Control (ICACC), March, 2010.pp.125-130
[6] Ojala, T., Pietikainen, M., and Maenpaa, T., “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns", IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, Jul. 2002, pp. 971–987
[7] Huang, D., Shan, C., Ardabilian, M., Wang, Y. and Chen, L., "Local binary patterns and its application to facial image analysis: a survey", IEEE Transaction on Systems, Man, and Cybernetics - Part C: Applications and Reviews, vol.41, no.6, November, 2011. pp.765-781
[8] Yang, Z. and Ai, H., "Demographic classification with local binary patterns", Proceedings of the 2007 International Conference on Advances in Biometrics (ICB'07), Seoul, Korea, August, 2007, pp. 464- 473
[9] Jassim, S. A., “Wavelet-based Face Recognition Schemes”, Book Chapter in "Face Recognition" Ed Milos Oravic, INTECH, ISBN 978- 953-7619-00-X, (2010).
[10] Shen, L. and Bai, L., "A review on Gabor wavelets for face recognition", Journal of Pattern Analysis and Applications, vol.9, no.2, 2006, pp273- 292
[11] Utsumi, Y., Iwai, Y. and Yachida, M., "Performance evaluation of face recognition in the wavelet domain", Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, October, Beijing, China, 2006, pp3344-3351
[12] Bagherian, E. and Rahmat, R. W., "Facial feature extraction for face recognition: a review", Int. Symposium on Information Technology, ITSim, 2008. No. 2(2). – P. 1–9
[13] Burton, AM, White, D., and McNeill, A. "The Glasgow face matching test. Behavior research methods", 2010;42(1), pp286-291.
[14] Kasinski, A., Florek, A., and Schmidt, A., "The PUT face database", Image Processing and Communications., 2008;13(3-4), pp59-64.
[15] Wang, X. and Tang, X. "Face photo-sketch synthesis and recognition", Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2009;31(11), pp1955-1967.
[16] http://viscog.hku.hk/facedb.htm, visited Feberuary 2013.
[17] Milborrow, S., Morkel, J. and Nicolls, F. "The MUCT landmarked face database", Pattern Recognition Association of South Africa, 2010
[18] Riccio, D., Tortora, G., De Marsico, M., and Wechsler, H., "EGA— Ethnicity, gender and age, a pre-annotated face database", 2012 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS), 2012
[19] Sellahewa, H. and Jassim, S. A. “Performance evaluation of waveletbased face verification on a PDA-recorded database”, Proc. Mobile Multimedia/Image Processing for Military and Security Applications, SPIE vol. 6250, 62500A, April 2006.
[20] Roofo, F. "An investigation in ethical facial characteristics for enhancing facial images", MSc Thesis, Applied Computing Department, University of Buckingham, June 2012.
[21] Elisseeff, A., and Pontil, M., "Leave-one-out error and stability of learning algorithms with applications.", NATO science series sub series iii computer and systems sciences 190 (2003), pp111-130.
[22] Mustafa, S., "Ethnicity Recognition from Face Images", MSc Thesis, Applied Computing Department, University of Buckingham, December 2007
[23] Al-Assam, H., Abboud, A., Sellahewa, H. and Jassim, S. A., "Exploiting relative entropy and quality analysis in cumulative partial biometric fusion", Transactions on data hiding and multimedia security VIII, Lecture notes in Computer Science, Springer, Vol 7228, pp. 1-18, March 2012
[24] Tariq, U., Hu, Y., Huang, T.S., "Gender and ethnicity identification from silhouetted face profiles", 16th IEEE International Conference on Image Processing (ICIP), vol.7, no.10, Nov. 2009, pp.2441-2444