Imerging local feature and fuzzy weighting for 2DPCA face recognition

Two Dimensional Principal Component Analysis (2DPCA) extracts the global feature of human face, but the local feature is very important to face recognition. In this paper, a method of imerging local feature and fuzzy weighting for 2DPCA face recognition was proposed. Firstly, two local feature areas — Upper area and Tzone area were divided, 2DPCA analysis is made to the view picture image and two regions independently. After the initial classify results were fuzzy weighted, minimum distance classification was used for face recognition, the purpose of unifying local feature and overall feature is carried on, the status of eye, nose, mouth and so on local features in the recognition is prominent. The experiments on ORL face databases demonstrate the proposed method's effectiveness and feasibility.

[1]  Do-Hyung Kim,et al.  Real-time face verification using multiple feature combination and a support vector machine supervisor , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[2]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[3]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[5]  Vijayan K. Asari,et al.  An improved face recognition technique based on modular PCA approach , 2004, Pattern Recognit. Lett..

[6]  Qian Xu,et al.  Adaptively Weighted 2DPCA Based on Local Feature for Face Recognition , 2008, 2008 Fourth International Conference on Natural Computation.