FACE RECOGNITION BASED ON TEXTURE ANALYSIS USING ROBUST LOCAL BINARY PATTERN

NAGARAJA S.¹, PRABHAKAR C.J.^2
1Department of P.G. Studies and Research in Computer Science, Kuvempu University, Shankaraghatta- 577 451, Karnataka, India.
²Department of P.G. Studies and Research in Computer Science, Kuvempu University, Shankaraghatta- 577 451, Karnataka, India.

Received : 27-11-2013     Accepted : 24-12-2013     Published : 28-12-2013
Volume : 3     Issue : 1       Pages : 97 - 102
J Mach Learn Tech 3.1 (2013):97-102

In this paper, we proposed a technique for face Recognition based on texture analysis using Robust Local Binary Pattern (RLBP). The major demerits of original Local Binary Pattern (LBP) based face recognition methods is that they are sensitive to noise and two different structural patterns produce same LBP code. In order to overcome these demerits, we proposed to adapt RLBP for face recognition, in which the value of each centre pixel in a 3x3 local area of the image is replaced by its average local gray level. Compared to gray value, average local gray level is more robust to noise and illumination variants. The experiments are conducted on face images of two popular face databases such as ORL and Yale. Support vector machine (SVM) classifier is used for classification. The proposed method can achieve good results on ORL and Yale database of face.