Textural feature based face recognition for single training images

by: R Singh, M Vatsa, A Noore

Electronics Letters, Vol. 41, No. 11. (2005), pp. 640-641.

View FullText article

IEEE Explore

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

xyz_123

Find related articles with these CiteULike tags

face, recognition

Abstract

A novel face recognition algorithm using single training face image is proposed. The algorithm is based on textural features extracted using the 2D log Gabor wavelet. These features are encoded into a binary pattern to form a face template which is used for matching. Experimental results show that on the colour FERET database the accuracy of the proposed algorithm is higher than the local feature analysis (LFA) and correlation filter (CF) based face recognition algorithms even when the number of training images is reduced to one. In comparison with recent single training image based face recognition algorithms, the proposed 2D log Gabor wavelet based algorithm shows an improvement of more than 3% in accuracy.

@article{citeulike:957316, abstract = {A novel face recognition algorithm using single training face image is proposed. The algorithm is based on textural features extracted using the 2D log Gabor wavelet. These features are encoded into a binary pattern to form a face template which is used for matching. Experimental results show that on the colour FERET database the accuracy of the proposed algorithm is higher than the local feature analysis (LFA) and correlation filter (CF) based face recognition algorithms even when the number of training images is reduced to one. In comparison with recent single training image based face recognition algorithms, the proposed 2D log Gabor wavelet based algorithm shows an improvement of more than 3\% in accuracy.}, author = {Singh, R. and Vatsa, M. and Noore, A. }, citeulike-article-id = {957316}, journal = {Electronics Letters}, keywords = {face, recognition}, number = {11}, pages = {640--641}, posted-at = {2006-11-22 10:14:36}, priority = {3}, title = {Textural feature based face recognition for single training images}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1437871}, volume = {41}, year = {2005} }

RIS record

TY - JOUR ID - citeulike:957316 L3 - citeulike-article-id:957316 TI - Textural feature based face recognition for single training images JF - Electronics Letters VL - 41 IS - 11 SP - 640 EP - 641 N2 - A novel face recognition algorithm using single training face image is proposed. The algorithm is based on textural features extracted using the 2D log Gabor wavelet. These features are encoded into a binary pattern to form a face template which is used for matching. Experimental results show that on the colour FERET database the accuracy of the proposed algorithm is higher than the local feature analysis (LFA) and correlation filter (CF) based face recognition algorithms even when the number of training images is reduced to one. In comparison with recent single training image based face recognition algorithms, the proposed 2D log Gabor wavelet based algorithm shows an improvement of more than 3% in accuracy. KW - face KW - recognition AU - Singh, R AU - Vatsa, M AU - Noore, A PY - 2005/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1437871 ER -

RIS BibTeX