An Efficient Method for Face Recognition based on Fusion of Global and Local Feature Extraction

Face recognition is a process of identifying people from their face images. Face recognition technology has many applications such as ATM access, verification of credit card, video surveillance etc. In this paper, we propose a novel face recognition algorithm which exploits both local and global features for feature extraction. Local features are extracted by Gabor wavelets and for global feature extraction, contourlet transform is applied. Then statistical parameters for local and global features are calculated and both the features are combined. Finally face recognition is performed using distance classifier. This proposed algorithm is implemented using MATLAB. The experimental results on ORL face database demonstrate the efficiency of proposed method as 98.5% as against non-fusion face recognition schemes. Index Terms : Face recognition, contourlet transform, feature extraction, local features, global features.