Block-based Deep Belief Networks for face recognition

被引：1

作者：

Ch'ng, Sue Inn ^{[1
]}

Seng, Kah Phooi ^{[2
]}

Ang, Li-Minn ^{[3
]}

机构：

[1] Nottingham Univ Malaysia Campus, Sch Engn, Semyih 43500, Selangor, Malaysia

[2] Sunway Univ Malaysia, Sch Comp Technol, Petaling Jaya 46150, Selangor, Malaysia

[3] Edith Cowan Univ, Ctr Commun Engn Res, Churchlands, WA, Australia

来源：

INTERNATIONAL JOURNAL OF BIOMETRICS | 2012年 / 4卷 / 02期

关键词：

face recognition; DBNs; deep belief networks; image blocks; fusion scheme; expression variation; illumination variation; decision-level fusion; score-level fusion;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents research findings on the use of Deep Belief Networks (DBNs) for face recognition. Experiments were conducted to compare the performance of a DBN trained using whole images with that of several DBN trained using image blocks. Image blocks are obtained when the face images are divided into smaller blocks. The objective of using image blocks is to improve the performance of the present DBN to visual variations. To test this hypothesis, the proposed block-based DBN was tested on different databases, which contain a variety of visual variations. Simulation results on these databases show that the proposed block-based DBN is effective against lighting variation. The proposed approach is also compared with other illumination invariant methods and was found to demonstrate higher recognition accuracies.

引用

页码：130 / 143

页数：14

共 26 条

[1] Ahonen T., 2004, PATTERN RECOGNITION
[2] Face description with local binary patterns:: Application to face recognition
Ahonen, Timo
Hadid, Abdenour
Pietikainen, Matti
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) : 2037 - 2041
[3] Local appearance based face recognition method using block based steerable pyramid transform
El Aroussi, Mohamed
El Hassouni, Mohammed
Ghouzali, Sanaa
Rziza, Mohammed
Aboutajdine, Driss
[J]. SIGNAL PROCESSING, 2011, 91 (01) : 38 - 50
[4] From few to many: Illumination cone models for face recognition under variable lighting and pose
Georghiades, AS
Belhumeur, PN
Kriegman, DJ
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (06) : 643 - 660
[5] An improved face recognition technique based on modular PCA approach
Gottumukkal, R
Asari, VK
[J]. PATTERN RECOGNITION LETTERS, 2004, 25 (04) : 429 - 436
[6] HINTON G, 2010, 2010003 U TOR MACH L
[7] Reducing the dimensionality of data with neural networks
Hinton, G. E.
Salakhutdinov, R. R.
[J]. SCIENCE, 2006, 313 (5786) : 504 - 507
[8] Training products of experts by minimizing contrastive divergence
Hinton, GE
[J]. NEURAL COMPUTATION, 2002, 14 (08) : 1771 - 1800
[9] A fast learning algorithm for deep belief nets
Hinton, Geoffrey E.
Osindero, Simon
Teh, Yee-Whye
[J]. NEURAL COMPUTATION, 2006, 18 (07) : 1527 - 1554
[10] Larochelle H., 2007, ICML, P473, DOI DOI 10.1145/1273496.1273556

← 1 2 3 →