Face Recognition Based on Deep Belief Network Combined with Center-Symmetric Local Binary Pattern
Human face recognition performances usually drops heavily due to pose variation and other factors. The representative deep learning method Deep Belief Network (DBN) has been proven to be an effective method to extract information-rich features of face ima
- PDF / 367,518 Bytes
- 7 Pages / 439.37 x 666.142 pts Page_size
- 94 Downloads / 232 Views
Abstract Human face recognition performances usually drops heavily due to pose variation and other factors. The representative deep learning method Deep Belief Network (DBN) has been proven to be an effective method to extract informationrich features of face image for recognition. However the DBN usually ignore the local features of image which are proven to be important for face recognition. Hence, this paper proposed a novel approach combined with local feature Center-Symmetric Local Binary Pattern (CS-LBP) and DBN. CS-LBP is applied to extract local texture features of face image. Then the extracted features are used as the input of Deep Belief Network instead of face image. The network structure and parameters are trained to obtain the final network model for recognition. A large amount of experiments are conducted on the ORL face database, and the experimental results show that compared with LBP, LBP combined with DBN and DBN, the proposed method has a significant improvement on recognition rates and can be a feasible way to combat with pose variation. Keywords Face recognition
Pose variation CS-LBP DBN
1 Introduction As a biometric technology, face has many distinct advantages compared with other biometric characteristics: it can be captured from a long distance which is friendly and convenience especially for the information security or access control application and it also has a wealthy structure and relatively larger area which is not easily C. Li (&) J. Wang W. Tang S. Zhao College of Computer Science, North China University of Technology, Beijing, China e-mail: [email protected] W. Wei College of Electronic and Information Engineering, North China University of Technology, Beijing, China © Springer Science+Business Media Singapore 2016 J.J. (Jong Hyuk) Park et al. (eds.), Advanced Multimedia and Ubiquitous Engineering, Lecture Notes in Electrical Engineering 393, DOI 10.1007/978-981-10-1536-6_37
277
278
C. Li et al.
to be occluded. Hence face recognition has becoming an indispensable biological authentication method and attracting many attentions. During the last decades, many face recognition approaches have been proposed and can be roughly divided into two types: pixel-based approach and feature-based approach [1]. The Principle component analysis (PCA), Linear Discriminant Analysis (LDA) and Independent Component Analysis (ICA) methods are the most typical pixel-based methods and have been proved to be effective for recognition with large databases. The feature-based approach mainly include Local Binary Pattern (LBP), Gabor, SIFT and their modified approaches. Most the above methods can achieve satisfying recognition result upon frontal and high resolution face image. However the feature extraction methods usually rely on artificial selection. Besides, to extract more robust deep-level features in order to express face information more effectively is still difficult. Hence face recognition performances usually drops heavily due to pose variation and other factors under unconstrained e
Data Loading...
