Face Recognition Using Local and Global Features
- PDF / 1,239,358 Bytes
- 12 Pages / 600 x 792 pts Page_size
- 67 Downloads / 249 Views
Face Recognition Using Local and Global Features Jian Huang Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong Email: [email protected]
Pong C. Yuen Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong Email: [email protected]
J. H. Lai Department of Mathematics, Zhongshan University, Guangzhou 510275, China Email: [email protected]
Chun-hung Li Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong Email: [email protected] Received 30 October 2002; Revised 24 September 2003 The combining classifier approach has proved to be a proper way for improving recognition performance in the last two decades. This paper proposes to combine local and global facial features for face recognition. In particular, this paper addresses three issues in combining classifiers, namely, the normalization of the classifier output, selection of classifier(s) for recognition, and the weighting of each classifier. For the first issue, as the scales of each classifier’s output are different, this paper proposes two methods, namely, linear-exponential normalization method and distribution-weighted Gaussian normalization method, in normalizing the outputs. Second, although combining different classifiers can improve the performance, we found that some classifiers are redundant and may even degrade the recognition performance. Along this direction, we develop a simple but effective algorithm for classifiers selection. Finally, the existing methods assume that each classifier is equally weighted. This paper suggests a weighted combination of classifiers based on Kittler’s combining classifier framework. Four popular face recognition methods, namely, eigenface, spectroface, independent component analysis (ICA), and Gabor jet are selected for combination and three popular face databases, namely, Yale database, Olivetti Research Laboratory (ORL) database, and the FERET database, are selected for evaluation. The experimental results show that the proposed method has 5–7% accuracy improvement. Keywords and phrases: local and global features, face recognition, combining classifier.
1.
INTRODUCTION
Face recognition research started in the late 70s and has become one of the active and exciting research areas in computer science and information technology areas since 1990. Basically, there are two major approaches in automatic recognition of faces by computer [1, 2], namely, constituent-based recognition (we called as local feature approach) and facebased recognition (we called as global feature approach). A number of face recognition algorithms/systems have been developed in the last decade. The common approach is to develop a single, sophisticated, and complex algorithm to handle one or more face variations. However, developing a single algorithm to handle all variations (including pose variation, luminance variation, light noise, etc.) is not easy. It is
known that different classifiers have their own characters to handle differen
Data Loading...
