False match elimination for face recognition based on SIFT algorithm

Abstract

ABSTRACT The SIFT (Scale Invariant Feature Transform) is a well known algorithm used to detect and describe local features in images. It is invariant to image scale, rotation and robust to the noise and illumination. In this paper, a novel method used for face recognition based on SIFT is proposed, which combines the optimization of SIFT, mutual matching and Progressive Sample Consensus (PROSAC) together and can e liminate the false matches of face recognition effectively. Experiments on ORL face database show that many false matches can be eliminated and better recognition rate is achieved. Keywords ufalse match elimination; SI FT; face recognition; PROSAC 1. INTRODUCTION Nowadays, it has raised a heated research on varied biomet rics. Compared to iris and fingerprint recognition, face recognition is appealing because it achieves relatively high accuracy, potentially demands much less user cooperation and human supervision. It is therefore less invasive and can be potentially cheap with fast processing speed. But in practice, the advantages are not apparent because of the technology bottleneck