Bayesian edge-texture feature descriptor for human face recognition

Abstract

This thesis work describes a novel feature descriptor named Conditional Bayes Conjunctional Edge-Texture and Texture-Edge (CBCETTE) feature extractor for human face recognition. It is based on Euclidean inter-distances between the local centre of mass (LCOM) and pixels, which is proficient in creating an optimal feature set by combining edge and texture inclusive of invariant to illumination, rotation, and noise. Initially, the image is divided into blocks of size 3 × 3 and for each block, a local centre of mass (LCOM) is derived initially from the original image. Using this local centre of mass, from each block image an edge image and a texture image is extracted using a novel approach on the basis of the direction of light. Subsequently from the edge image and texture image, a probabilistic edge image and a probabilistic texture image are derived further to enunciate the combined edge texture feature set. Finally, Bayes’ conditional probabilistic approach is applied on both the probabilistic edge and the probabilistic texture image to obtain the probabilistic edge-texture and vice-versa feature set. The optimum feature set is the conjunction of the two probabilistic feature sets. This final optimum conjunction probabilistic feature set is finally used for classification purposes. It has been successfully tested on various challenging databases like Yale B face database, Extended Yale B face database, Yale face database, Faces95 database, and ORL database. It provides the accuracy of 99.38%, 98.77%, 97.58%, 97.92%, and 93.75% respectively on Yale B face database, Extended Yale B face database, Yale face database, Faces95 database, and ORL database that exhibits supremacy of the proposed strategy for human face recognition under various conditions.