Face recognition method based on support vector machine and particle swarm optimization

被引:69
作者
Jin Wei [1 ]
Zhang Jian-qi [1 ]
Zhang Xiang [1 ]
机构
[1] Xidian Univ, Sch Technol Phys, Xian 710071, Peoples R China
关键词
Face recognition; Recognition accuracy; Non-linear; Support vector machine; NEURAL-NETWORK; CLASSIFICATION;
D O I
10.1016/j.eswa.2010.09.108
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Face recognition belongs to the problem of non-linear, which increases the difficulty of its recognition. Support vector machine (SVM) is a novel machine learning method, which can find global optimum solutions for problems with small training samples and non-linear, so support vector machine has a good application prospect in face recognition. In the study, the novel face recognition method based on support vector machine and particle swarm optimization (PSO-SVM) is presented. In PSO-SVM, PSO is used to simultaneously optimize the parameters of SVM. FERET human face database is adopted to study the face recognition performance of PSO-SVM, and the proposed method is compared with SVM, BPNN. The experimental indicates that PSO-SVM has higher face recognition accuracy than normal SVM, BPNN. Therefore, PSO-SVM is well chosen in face recognition. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码:4390 / 4393
页数:4
相关论文
共 11 条
[1]   A neural network face recognition system [J].
Aitkenhead, MJ ;
McDonald, AJS .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2003, 16 (03) :167-176
[2]   A software tool for teaching of particle swarm optimization fundamentals [J].
Coelho, Leandro dos Santos ;
Sierakowski, Cezar Augusto .
ADVANCES IN ENGINEERING SOFTWARE, 2008, 39 (11) :877-887
[3]   Particle swarm optimization approach to portfolio optimization [J].
Cura, Tunchan .
NONLINEAR ANALYSIS-REAL WORLD APPLICATIONS, 2009, 10 (04) :2396-2406
[4]   Model selection for support vector machine classification [J].
Gold, C ;
Sollich, P .
NEUROCOMPUTING, 2003, 55 (1-2) :221-249
[5]   Face recognition using a hybrid supervised unsupervised neural network [J].
Intrator, N ;
Reisfeld, D ;
Yeshurun, Y .
PATTERN RECOGNITION LETTERS, 1996, 17 (01) :67-76
[6]   A combinatorial particle swarm optimisation for solving permutation flowshop problems [J].
Jarboui, Bassem ;
Ibrahim, Saber ;
Siarry, Patrick ;
Rebai, Abdelwaheb .
COMPUTERS & INDUSTRIAL ENGINEERING, 2008, 54 (03) :526-538
[7]   Synchronous parallelization of Particle Swarm Optimization with digital pheromones [J].
Kalivarapu, Vijay ;
Foo, Jung-Leng ;
Winer, Eliot .
ADVANCES IN ENGINEERING SOFTWARE, 2009, 40 (10) :975-985
[8]   Incorporating prior knowledge in support vector machines for classification: A review [J].
Lauer, Fabien ;
Bloch, Gerard .
NEUROCOMPUTING, 2008, 71 (7-9) :1578-1594
[9]   Mapping specific habitats from remotely sensed imagery: Support vector machine and support vector data description based classification of coastal saltmarsh habitats [J].
Sanchez-Hernandez, Carolina ;
Boyd, Doreen S. ;
Foody, Giles M. .
ECOLOGICAL INFORMATICS, 2007, 2 (02) :83-88
[10]   Using backpropagation neural network for face recognition with 2D+3D hybrid information [J].
Sun, Te-Hsiu ;
Tien, Fang-Chih .
EXPERT SYSTEMS WITH APPLICATIONS, 2008, 35 (1-2) :361-372