Face Recognition Using Gabor Wavelets

摘要

Face recognition with variant pose, illumination and expression is a challenging problem. Robust face recognition requires the ability to recognize identity despite many variations in appearance the face can have. Today there exist many well known techniques for face recognition, each with its own inherent limitations. In this paper we present a novel approach to face recognition using Gabor wavelets. The Gabor image representation simulates the function of the human visual system, a design feature which may be important in the field of robotics and computer vision. The Gabor wavelets approach appears to be quite perspective and has several advantages such as invariance to homogenous illumination changes, small changes in head poise and robustness against facial hair, glasses. Experimental results show that the proposed method performs better than traditional approaches in terms of both efficiency and accuracy. It is worth mentioning that Gabor wavelets technique has recently been used not only for face recognition, but also for face tracking and face position estimation.