Facial recognition using histogram of Gabor phase patterns and self organizing maps

Abstract

Automatic person identification using face information is very challenging task in the field of computer vision. A simple and efficient face recognition approach based on Gabor phase pattern and Self Organizing Maps is presented here. Histogram of Gabor Phase Pattern is used in proposed approach for feature extraction and Self Organizing maps are used as a classifier to identify whether the given grayscale image belongs to a particular class or not. In contrast to other feature extraction techniques, faster results are obtained using Histogram of Gabor Phase Patterns as feature detection occurs automatically without the need of any training procedure. A series of extensive experiments performed on various databases on MATLAB shows that proposed approach achieved a recognition rate of 97.33%, 96.49% and 94.20% for 7 consecutive trials on ORL, YALE and JAFFE databases respectively. It is demonstrated through experimental results that the proposed approach yields significant gain in terms of computational simplicity and effective accuracy.