An Efficient Method for Face Recognition based on Fusion of Global and Local Feature Extraction
E. Gomathi1, K. Baskaran2
1Er. E. Gomathi, Department of Electronics and Communication Engineering, Karpagam College of Engineering, Coimbatore, India.
2Dr. K. Baskaran, Department of Computer Science and Engineering, Government College of Technology, Coimbatore, India.
Manuscript received on November 02, 2014. | Revised Manuscript received on November 04, 2014. | Manuscript published on November 05, 2014. | PP: 56-60 | Volume-4 Issue-5, November 2014. | Retrieval Number: D2354094414/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: 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.
Keywords: Face recognition, contourlet transform, feature extraction, local features, global features.