A Novel Local Feature Extraction Algorithm Based on Gabor Wavelet Transform

Abstract

Aiming at the problem that the feature extraction method based on Gabor wavelet transform makes the feature vector dimension higher, a novel method named GCLBP (Gabor-CSLBP) is proposed in this paper. Based on Gabor wavelet transform, the proposed algorithm is a local feature extraction method, which extracted a new kind of feature through applying the idea of CS-LBP (Center-Symmetric Local Binary Pattern) into the resulted sub-images of Gabor transform. The feature vector obtained by the GCLBP method combines the advantages of Gabor wavelet transform and CS-LBP, which not only reduces the dimension of the feature vector, but also improves the robustness of image variation. The proposed method is evaluated by extensive experiments on benchmark databases CMU PIE, and Extended Yale B. The experimental results show that the proposed method -- GCLBP, can significantly improve the face recognition rate under complex illumination.