Biologically Inspired Tensor Features

被引:18
作者
Mu, Yang [1 ]
Tao, Dacheng [1 ]
Li, Xuelong [2 ]
Murtagh, Fionn [3 ]
机构
[1] Nanyang Technol Univ, Singapore 639798, Singapore
[2] Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China
[3] Univ London, Dept Comp Sci, Egham TW20 0EX, Surrey, England
关键词
Biologically inspired features; C1; units; Manifold learning; Discriminative locality alignment; Face recognition; OBJECT RECOGNITION; FACE; CLASSIFICATION; EIGENFACES; MODELS;
D O I
10.1007/s12559-009-9028-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of object recognition in the primate's visual cortex. Therefore, it is time to reconsider face recognition by using biologically inspired features. In this paper, we represent face images by utilizing the C1 units, which correspond to complex cells in the visual cortex, and pool over S1 units by using a maximum operation to reserve only the maximum response of each local area of S1 units. The new representation is termed C1 Face. Because C1 Face is naturally a third-order tensor (or a three dimensional array), we propose three-way discriminative locality alignment (TWDLA), an extension of the discriminative locality alignment, which is a top-level discriminate manifold learning-based subspace learning algorithm. TWDLA has the following advantages: (1) it takes third-order tensors as input directly so the structure information can be well preserved; (2) it models the local geometry over every modality of the input tensors so the spatial relations of input tensors within a class can be preserved; (3) it maximizes the margin between a tensor and tensors from other classes over each modality so it performs well for recognition tasks and (4) it has no under sampling problem. Extensive experiments on YALE and FERET datasets show (1) the proposed C1Face representation can better represent face images than raw pixels and (2) TWDLA can duly preserve both the local geometry and the discriminative information over every modality for recognition.
引用
收藏
页码:327 / 341
页数:15
相关论文
共 50 条
[41]   A biologically inspired model mimicking the memory and two distinct pathways of face perception [J].
Xi, Xuanyang ;
Yin, Peijie ;
Qiao, Hong ;
Li, Yinlin ;
Feng, Wensen .
NEUROCOMPUTING, 2016, 205 :349-359
[42]   B-HMAX: A fast binary biologically inspired model for object recognition [J].
Zhang, Hua-Zhen ;
Lu, Yan-Feng ;
Kang, Tae-Koo ;
Lim, Myo-Taeg .
NEUROCOMPUTING, 2016, 218 :242-250
[43]   A Novel Biologically Inspired Visual Cognition Model: Automatic Extraction of Semantics, Formation of Integrated Concepts, and Reselection Features for Ambiguity [J].
Yin, Peijie ;
Qiao, Hong ;
Wu, Wei ;
Qi, Lu ;
Li, Yinlin ;
Zhong, Shanlin ;
Zhang, Bo .
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2018, 10 (02) :420-431
[44]   Traffic sign recognition method with biologically inspired transform [J].
Yu, Lingli ;
Xia, Xumei ;
Zhou, Kaijun ;
Long, Ziwei ;
Chen, Baifan .
2017 IEEE 7TH ANNUAL INTERNATIONAL CONFERENCE ON CYBER TECHNOLOGY IN AUTOMATION, CONTROL, AND INTELLIGENT SYSTEMS (CYBER), 2017, :225-230
[45]   Improving invariance in visual classification with biologically inspired mechanism [J].
Tang, Tang ;
Qiao, Hong .
NEUROCOMPUTING, 2014, 133 :328-341
[46]   A biologically inspired visual integrated model for image classification [J].
Wei, Bing ;
Hao, Kuangrong ;
Gao, Lei ;
Tang, Xue-song ;
Zhao, Yudi .
NEUROCOMPUTING, 2020, 405 :103-113
[47]   A Novel Biologically Inspired Structural Model for Feature Correspondence [J].
Lu, Yan-Feng ;
Yang, Xu ;
Li, Yi ;
Yu, Qian ;
Liu, Zhi-Yong ;
Qiao, Hong .
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2023, 15 (02) :844-854
[48]   Exploring biologically inspired shallow model for visual classification [J].
Tang, Tang ;
Qiao, Hong .
SIGNAL PROCESSING, 2014, 105 :1-11
[49]   BIOLOGICALLY INSPIRED FUZZY FORECASTING: A NEW FORECASTING METHODOLOGY [J].
Jeng, Don Jyh-Fu ;
Watada, Junzo ;
Wu, Berlin .
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2009, 5 (12B) :4835-4844
[50]   BIOLOGICALLY INSPIRED FAULT ADAPTIVE STRATEGIES FOR ENGINEERED SYSTEMS [J].
Jensen, David Charles ;
Huisman, Nicholas .
DS 80-2 PROCEEDINGS OF THE 20TH INTERNATIONAL CONFERENCE ON ENGINEERING DESIGN (ICED 15) VOL 2: DESIGN THEORY AND RESEARCH METHODOLOGY DESIGN PROCESSES, 2015,