模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2017, Vol. 30 Issue (7): 653-662    DOI: 10.16451/j.cnki.issn1003-6059.201707008
Orignal Article Current Issue| Next Issue| Archive| Adv Search |
Sparse Feature Extraction Model Based on Deep and Symmetric Subspace Learning
HU Zhengping, CHEN Junling, WANG Meng, SUN Zhe
School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004

Download: PDF (862 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  An algorithm of sparse feature extraction model is proposed based on deep and symmetric subspace learning. According to the theory of deep subspace learning, the constraints of symmetry and sparsity are introduced and the deep map network is built to extract features. Firstly, the basic subspace mapping matrix is constructed by minimizing the reconstruction error and the constraints of symmetry and sparsity are introduced for training. Next, the basic subspace model based on deep learning is reformed, and the deep symmetric sparse feature extraction model is built. These feature extraction results from different layers are merged to obtain the multi-layered deep symmetric subspace sparse feature. The experimental results on face databases show that the proposed algorithm achieves high recognition rates and strong robustness in illumination, expression and pose. Furthermore, compared with the convolutional neural networks, the proposed algorithm has the advantages of simple structure and high convergent rate.
Key wordsDeep Learning      Symmetry Constraint      Multi-layered Fusion      Sparse Optimization     
ZTFLH: TP 391.41  
Fund:Supported by National Natural Science Foundation of China(No.61071199), Natural Science Foundation of Hebei Province(No.F2016203422)
Corresponding Authors: (HU Zhengping(Corresponding author), born in 1970, Ph.D., professor. His research interests include pattern recognition.)   
About author:: (HU Zhengping(Corresponding author), born in 1970, Ph.D., professor. His research interests include pattern recognition.)
(CHEN Junling, born in 1991, master student. His research interests include deep learning.)
(WANG Meng, born in 1982, Ph.D. candidate, lecturer. Her research interests include pattern recognition.)
(SUN Zhe, born in 1990, Ph.D. candidate. Her research interests include pattern recognition.)
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
HU Zhengping
CHEN Junling
WANG Meng
SUN Zhe
Cite this article:   
HU Zhengping,CHEN Junling,WANG Meng等. Sparse Feature Extraction Model Based on Deep and Symmetric Subspace Learning[J]. , 2017, 30(7): 653-662.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201707008      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2017/V30/I7/653
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn