Enhanced Face Recognition by Fusion of Global and Local Features under Varying Illumination

We propose a new method to enhance performance of face recognition under varying lightings by applying score-level fusion between global and local Fourier-Mellin Transform (FMT) features based SVM. An optimal method based Particle Swarm Optimization (PSO) is used to find optimal weights to fuse the aforementioned information at score-level. The results on Korean face database demonstrate that our proposed method outperforms standard global feature, local feature and other well-known methods. Specifically, the best recognition rate is, respectively, 89% and 85% for indoor and outdoor images.