Author : Yukti Bakhshi, Sukhvir Kaur and Prince Verma

Face recognition has recently grown its importance, especially during the past several years as one of the most successful applications of image analysis. It has been a fast growing, interesting and challenging area in real time applications. In last decades a large number of face recognition algorithms have been developed. In this paper an attempt is made to review methods used for face recognition- SIFT, SURF, PCA, PCA-SIFT, etc. for recognition and matching. Scale invariant feature transform (SIFT) used to extract distinct invariant features from images can be used to perform reliable matching. To overcome SIFT drawbacks PCA eigenfaces entered into SIFT. We described the basic process of face recognition system and improvement in matching the invariant faces in this paper. We are using SIFT and SURF to extract the features and then applying PCA to the image for the better performance in terms of rotation, pose and illumination. Performance can be seen on the basis of FAR, FRR, Recognition rate and Computation time. For the implementation of this proposed work we use the Image Processing Toolbox under MATLAB Software.

Keywords: Image Processing, Face Recognition, Face Recognition Algorithms, SIFT, SURF and PCA

Article published in International Journal of Current Engineering and Technology, Vol.6, No.2 (April-2016)