Using moment invariants and HMM in facial expression recognition

被引：67

作者：

Zhu, Y ^{[1
]}

De Silva, LC ^{[1
]}

Ko, CC ^{[1
]}

机构：

[1] Natl Univ Singapore, Dept Elect Engn, Singapore 119260, Singapore

来源：

PATTERN RECOGNITION LETTERS | 2002年 / 23卷 / 1-3期

关键词：

moment invariant; HMM; pattern recognition; facial expression; recognition;

D O I：

10.1016/S0167-8655(01)00108-8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Moment invariants are invariant under shifting, scaling and rotation. They are widely used in pattern recognition because of their discrimination power and robustness. HMM method is a natural and highly reliable way of recognition. In this paper, we have proposed a method of using moment invariants as features and HMM as recognition method in facial expression recognition. Sequences of four universal expressions, i.e. anger, disgust, happiness and surprise, are recognized. We were able to attain an accuracy as high as 96.77%. (C) 2002 Elsevier Science B.V, All rights reserved.

引用

页码：83 / 91

页数：9

共 10 条

[1] RECOGNITIVE ASPECTS OF MOMENT INVARIANTS
ABUMOSTAFA, YS
PSALTIS, D
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) : 698 - 706
[2] DESILVA LC, 1995, IEICE T INF SYST, VE78D, P1195
[3] VISUAL-PATTERN RECOGNITION BY MOMENT INVARIANTS
HU, M
[J]. IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (02): : 179 - &
[4] Linde Y, 1980, IEEE T COMMUNICATION, V28
[5] MASE K, 1991, IEICE TRANS COMMUN, V74, P3474
[6] OTSUKA T, 1996, IEEE INT WORKSH ROB, P323
[7] Rabiner L., 1993, Fundamentals of Speech Recognition
[8] A TUTORIAL ON HIDDEN MARKOV-MODELS AND SELECTED APPLICATIONS IN SPEECH RECOGNITION
RABINER, LR
[J]. PROCEEDINGS OF THE IEEE, 1989, 77 (02) : 257 - 286
[9] SAKAGUCHI T, ACCV 95, P423
[10] YACOOB Y, P IEEE COMP SOC C CO, P70

← 1 →