Cyber Times International Journal of Technology & Management

In this paper, an attempt has made on Hybrid method for face recognition which combines global information( raw face information) and local information(constituent information). The proposed method consists of three stages: In the first stage, input images are read and enhanced by filtering and clipping method. In the second stage, Features of images are extracted in two forms- Global and Local form using Genetic Algorithm. In the third stage, extracted images are fed in to the Feed - Forward Neural Network – Back Propagation Network for recognition. This proposed method is experimentally tested on images in the FERET database and efficiency of the proposed method is better than the existing method only for local feature or global features. In the conclusion, this paper also suggests the future research work.