Face Recognition Using Robust Rule Based Local Binary Patter
O. Rama Devi1, V. Sree Lasya2, V. Siddhartha2
Citation : O. Rama Devi, V. Sree Lasya, V. Siddhartha, Face Recognition Using Robust Rule Based Local Binary Patter International Journal of Research Studies in Computer Science and Engineering 2015, 2(3) : 9-12
A novel efficient and robust methodology for quick face recognition by using Rule based Local Binary Pattern (RLBP) has been presented. The face image is said to be divided into a number of 3x3 regions, called as micro patterns, indicating the structure of the gray level pixels within a neighborhood to describe the spatial context of represented as rule number to evaluate the membership degree of the central pixel to the others within a neighborhood. A Local face distributor for each of the 3x3 neighborhood, called LBP descriptor, is obtained by applying Rules from which the RLBP feature distributions are extracted. Use of contributes to more than a single bin in the distribution of LBP values in the feature vector. The recognition is performed using a nearest neighbor classifier in the computed feature space. Experiments clearly show that the use of RLBP leads to improved reliable face recognition than to the original methods, LBP and Rule Based LBP.