Walsh-Hadamard Transform for Facial Feature Extraction in Face Recognition

Authors: M. Hassan, I. Osman, M. Yahia

Abstract:

This Paper proposes a new facial feature extraction approach, Wash-Hadamard Transform (WHT). This approach is based on correlation between local pixels of the face image. Its primary advantage is the simplicity of its computation. The paper compares the proposed approach, WHT, which was traditionally used in data compression with two other known approaches: the Principal Component Analysis (PCA) and the Discrete Cosine Transform (DCT) using the face database of Olivetti Research Laboratory (ORL). In spite of its simple computation, the proposed algorithm (WHT) gave very close results to those obtained by the PCA and DCT. This paper initiates the research into WHT and the family of frequency transforms and examines their suitability for feature extraction in face recognition applications.

Keywords: Face Recognition, Facial Feature Extraction, Principal Component Analysis, and Discrete Cosine Transform, Wash-Hadamard Transform.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1057297

References:

[1] Almas M. , Younus M. and Basit A., Anew Approach to Face Recognition Using Dual Dimension Reduction, International Journal of Signal Processing Volume 2 Number 1,ISBN 1304-4494, 2005.
[2] Conrad S., Kuldip K., Fast Features for Face Authentication Under Illumination Direction Changes, Pattern Recognition Letters 2, 2409-2419, 2003.
[3] Eicheler, S., Muller, S. and Rigoll, G., Recognition on JPEG Compressed Face Images Based on Statistical Methods, Image Vision Compute. 18(4), 279-287 ,2000.
[4] Hazem K.,Rainer S., Local Appearance Based Face Recognition Using Discrete Cosine Transform, 13th European Signal Processing Conference (EUSIPCO), Antalia, 2005.
[5] Kresimir,D.,Mislav,G.,Panos,L,Appearnce-based Statistical Methods for Face Recognition,47 th International Symposium ELMAR-2005,Zedar,Croatia, June 2005.
[6] Musa, M., Towards Finding Optimal Mixture of Subspaces for Data Classification, PhD Thesis ,The Middle East Technical University, Turkey,Oct,2003.
[7] O.R.L(ORL), www.mambo.ucsc.edu/psl/olivetti.html.
[8] O.R.L(ORL),www.uk.research.att.com/facedatabase.html .
[9] Penio S. and Joseph J , Local Feature Analysis: A general Statistical Theory for Object Representation, Network: Computation in Neural Systems 7(3),p 477-500, 1996.
[10] Picard R. and Kabir,T.,Finding Similar Patterns in large image databases, M.I.T,Technical Report No. 205, IEEE ICASSP ,Minneapolis, MN, Vol. V.,PP.161-164, Apr. 1993.
[11] Rauf K.,Vladimir A., and Leonid P. ,Face Recognition Algorithm on the Basis of truncated Walsh-Hadamard Transform and Synthetic Discriminant Functions, Proc. 6th International Conf. on Face Recognition and Gesture Recognition ,Seoul, Korea, 2004.
[12] Ross, B.,Kai, S,Bruce A.,and Geof, H.,A Nonparametric Statistical Comparison of Principal Component and Linear Discriminant subspaces for Face Recognition, IEEE Society Conference on Computer Vision and Pattern Recognition, Vol. 1, p535 ,2001.
[13] Scott E., Computer Vision and Image Processing ,Prentice Hall PTR, Prentice Hall,Inc,Upper Saddle River,NJ 07458,ISBN :0-13-264-599-8,USA,1999.
[14] Shaokang, S.,Brain, C. and Sai, S. ,Face Recognition With APCA in Variant Illuminations, Workshop on signal processing and its applications, Brisbane, Dec 2002.
[15] Turk,M., and Alex, P., Face Recognition using Eignfaces, Proc. IEEE Conf. on Computer Vision and pattern Recognition, pp.586-591, 1991.
[16] Turk M. and Pentland A., Eigenfaces for Face Detection/Recognition , Journal of Cognitive Neuroscience ,Vol. 3, No. 1 , pp. 71-86, 1991.
[17] Willie L. Scott, II, Block-Level Discrete Cosine Transform Coefficients for Autonomic Face Recognition, Ph.D Thesis Submitted to Graduate Faculty of Louisiana State U. and Agricultural and Mechanical Collage , USA, May 2003 .
[18] Wellie L. Scott,II, The NN Approach to Autonomic Face Recognition, print arXiv:CS/0603042,2006cs, 2006.
[19] Zhao,S.,Chellappa,R.,Multiple exampler Discriminant Analysis for Face Recognition , In proc. of Intl. Conf. on Pattern Recognition, August 2004.
[20] Zhao,S.,Chellappa, R.,Phillips, J.and Rosenfeld, A., Face Recognition: A literature Survey, ACM Computing Surveys ,Vol 35, No.4, pp.399-458, Dec/2003.
[21] Zhengju P., Hamid B., High speed Face Recognition based on Discrete Cosine Transforms and Neural Networks, IEEE Trans. on Pattern Analysis & Machine Intelligence, 1999.
[22] Zhengju P., Rod A., Hamid B., Dimensionality Reduction of Face Images Using Discrete Cosine Transforms for Recognition, IEEE Conf. on Computer Vision and A Pattern Recognition (CVPR2000), South Carolina, USA, 2000.