Abstract

Paper Title/ Authors Name Download View

HUMAN FACE RECOGNITION USING WEIGHTED Co-OCCURRENCE HISTOGRAM OF ORIENTED GRADIENTS (W-CoHOG)

Beesetty G P Hima Ketan, ValliKumari Vatsavayi


Face Recognition is an essential task in many areas. A method of face recognition using Weighted Co-occurrence Histogram of Oriented Gradient (W-CoHOG) is presented in this paper. In the recent times, the approach of Co-occurrence Histogram of Oriented Gradient (CoHOG) is being applied widely in face recognition. In this paper, we are applying Weighted Co-occurrence Histogram Oriented Gradient (W-CoHOG). W-CoHOG is an extension of CoHOG and it takes magnitude also instead of only considering pair of orientations one where in Weighted Co-occurrence matrix is computed and histograms are calculated. W-CoHOG have recognition accuracy higher than CoHOG. In this paper, weighted co-occurrence histogram of oriented gradients (W-CoHOG) concept is introduced for computing also the magnitude to improve the accuracy. Magnitude value is included to influence the feature vector to achieve better performance than existing methods. Experiments were conducted on two face recognition datasets namely YALE and CALTECH. The experiment results support our approach.