Spatial regularization in subspace learning for face recognition: implicit vs. explicit

被引:2
作者
Zhu, Yulian [1 ,2 ]
Chen, Songcan [2 ]
Tian, Qing [2 ]
机构
[1] Nanjing Univ Aeronaut & Astronaut, Ctr Comp, Nanjing 211106, Jiangsu, Peoples R China
[2] Nanjing Univ Aeronaut & Astronaut, Coll Comp Sci & Technol, Nanjing 210016, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
Face recognition; Implicit spatial regularization (ISR); Explicit spatial regularization (ESR); Subspace learning; Linear discriminant analysis (LDA); Locality preserving projection (LPP); 3-D OBJECT RETRIEVAL; SMOOTH SUBSPACE;
D O I
10.1016/j.neucom.2015.09.028
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In applying traditional statistical method to face recognition, each original face image is often vectorized as a vector. But such a vectorization not only leads to high-dimensionality, thus small sample size (SSS) problem, but also loses the original spatial relationship between image pixels. It has been proved that spatial regularization (SR) is an effective means to compensate the loss of such relationship and at the same time, and mitigate SSS problem by explicitly imposing spatial constraints. However, SR still suffers from two main problems: one is high computational cost due to high dimensionality and the other is the selection of the key regularization factors controlling the spatial regularization and thus learning performance. Accordingly, in this paper, we provide a new idea, coined as implicit spatial regularization (ISR), to avoid losing the spatial relationship between image pixels and deal with SSS problem simultaneously for face recognition. Different from explicit spatial regularization (ESR), which introduces directly spatial regularization term and is based on vector representation, the proposed ISR constrains spatial smoothness within each small image region by reshaping image and then executing 2D-based feature extraction methods. Specifically, we follow the same assumption as made in SSSL (a typical ESR method) that a small image region around an image pixel is smooth, and reshape each original image into a new matrix whose each column corresponds to a vectorized small image region, and then we extract features from the newly-formed matrix using any off-the-shelf 2D-based method which can take the relationship between pixels in the same row or column into account, such that the original spatial relationship within the neighboring region can be greatly retained. Since ISR does not impose constraint items, compared with ESR, ISR not only avoids the selection of the troublesome regularization parameter, but also greatly reduces computational cost. Experimental results on four face databases show that the proposed ISR can achieve competitive performance as SSSL but with lower computational cost. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:1554 / 1564
页数:11
相关论文
共 36 条
[21]   Comparison of Random Subspace and Voting Ensemble Machine Learning Methods for Face Recognition [J].
Yaman, Mehmet Akif ;
Subasi, Abdulhamit ;
Rattay, Frank .
SYMMETRY-BASEL, 2018, 10 (11)
[22]   Multi-modal Subspace Learning with Dropout regularization for Cross-modal Recognition and Retrieval [J].
Cao, Guanqun ;
Waris, Muhammad Adeel ;
Iosifidis, Alexandros ;
Gabbouj, Moncef .
2016 SIXTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), 2016,
[23]   2D face recognition based on supervised subspace learning from 3D models [J].
Franco, Annalisa ;
Maio, Dario ;
Maltoni, Davide .
PATTERN RECOGNITION, 2008, 41 (12) :3822-3833
[24]   From Local Geometry to Global Structure: Learning Latent Subspace for Low-resolution Face Image Recognition [J].
Shi, Jingang ;
Qi, Chun .
IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (05) :554-558
[25]   Face Recognition and Micro-expression Recognition Based on Discriminant Tensor Subspace Analysis Plus Extreme Learning Machine [J].
Su-Jing Wang ;
Hui-Ling Chen ;
Wen-Jing Yan ;
Yu-Hsin Chen ;
Xiaolan Fu .
Neural Processing Letters, 2014, 39 :25-43
[26]   Face Recognition and Micro-expression Recognition Based on Discriminant Tensor Subspace Analysis Plus Extreme Learning Machine [J].
Wang, Su-Jing ;
Chen, Hui-Ling ;
Yan, Wen-Jing ;
Chen, Yu-Hsin ;
Fu, Xiaolan .
NEURAL PROCESSING LETTERS, 2014, 39 (01) :25-43
[27]   Illumination normalization for face recognition - A comparative study of conventional vs. perception-inspired algorithms [J].
Dunker, Peter ;
Keller, Melanie .
BIOSIGNALS 2008: PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON BIO-INSPIRED SYSTEMS AND SIGNAL PROCESSING, VOL II, 2008, :237-243
[28]   Uncorrelated Discriminant Vectors vs. Orthogonal Discriminant Vectors in Appearance-based Face Recognition [J].
Song, Fengxi ;
Zheng, Rubin .
SECOND INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN, VOL 2, PROCEEDINGS, 2009, :446-449
[29]   2DPCA vs. 2DLDA: Face Recognition using Two-Dimensional Method [J].
Wang, Xiao-ming ;
Huang, Chang ;
Fang, Xiao-ying ;
Liu, Jin-gao .
2009 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, VOL II, PROCEEDINGS, 2009, :357-360
[30]   Cross-Batch Hard Example Mining With Pseudo Large Batch for ID vs. Spot Face Recognition [J].
Tan, Zichang ;
Liu, Ajian ;
Wan, Jun ;
Liu, Hao ;
Lei, Zhen ;
Guo, Guodong ;
Li, Stan Z. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :3224-3235