Walsh-Hadamard Transform for Facial Feature Extraction in Face Recognition

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.

[1]  M. Younus Javed,et al.  A New Approach to Face Recognition Using Dual Dimension Reduction , 2008 .

[2]  Kuldip K. Paliwal,et al.  Fast features for face authentication under illumination direction changes , 2003, Pattern Recognit. Lett..

[3]  Bruce A. Draper,et al.  A nonparametric statistical comparison of principal component and linear discriminant subspaces for face recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  Brian C. Lovell,et al.  Face Recognition with APCA in Variant Illuminations , 2002 .

[5]  Rauf Kh. Sadykhov,et al.  Face recognition algorithm on the basis of truncated Walsh-Hadamard transform and synthetic discriminant functions , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[6]  Willie L. Scott.  The NoN Approach to Autonomic Face Recognition , 2006, ArXiv.

[7]  Gerhard Rigoll,et al.  Recognition of JPEG compressed face images based on statistical methods , 2000, Image Vis. Comput..

[8]  Penio S. Penev,et al.  Local feature analysis: A general statistical theory for object representation , 1996 .

[9]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[10]  Rosalind W. Picard,et al.  Finding similar patterns in large image databases , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  Meng Joo Er,et al.  High-speed face recognition based on discrete cosine transform and RBF neural networks , 2005, IEEE Transactions on Neural Networks.

[12]  M. Grgic,et al.  Appearance-based statistical methods for face recognition , 2005, 47th International Symposium ELMAR, 2005..

[13]  Mohamed E. M. Musa.  Towards finding optimal mixture of subspaces for data classification ; Veri sınıflama için en iyi altuzay karışımlarının bulunmasına doğru , 2003 .

[14]  Rainer Stiefelhagen,et al.  Local appearance based face recognition using discrete cosine transform , 2005, 2005 13th European Signal Processing Conference.

[15]  Alex Waibel,et al.  Local Appearance-based 3D Face Recognition , 2006 .

[16]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[17]  Azriel Rosenfeld,et al.  Computer vision and image processing , 1992 .

[18]  Subhash Kak,et al.  Block-level discrete cosine transform coefficients for autonomic face recognition , 2003 .

[19]  Tim Morris,et al.  Computer Vision and Image Processing: 4th International Conference, CVIP 2019, Jaipur, India, September 27–29, 2019, Revised Selected Papers, Part I , 2020, CVIP.