Application of Kekre's fast code book generation algorithm for face recognition
Hemant B. Kekre, Ketan D. Shah, Tanuja Sarode · 2010
In this paper we propose fast face recognition system based on the Kekre's Fast Code book Generation (KFCG) method. This algorithm can be easily implemented and number of coefficients required for recognition reduces drastically compared to Eigen face approach. Thus computational burden decreases. We have compared the performance of KFCG with PCA. The algorithm is tested for different percentage of occlusion applied on various codebook sizes. Here we have tested proposed scheme on standard ORL database and locally generated unconstrained database of Indian faces. ORL database gave the accurate results and local database gave accuracy of 89% which is higher than PCA approach.