Facial Expression Recognition Based on Fusion of Local Features and Deep Belief Network

Wang Linlin; Liu Jinghao; Fu Xiaomei

doi:10.3788/LOP55.011002

Laser & Optoelectronics Progress, Volume. 55, Issue 1, 11002(2018)

Facial Expression Recognition Based on Fusion of Local Features and Deep Belief Network

Wang Linlin^1、*, Liu Jinghao¹, and Fu Xiaomei²

Author Affiliations

¹School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

²School of Marine Science and Technology, Tianjin University, Tianjin 300072, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Log-Gabor magnitude features of local facial expression image

Download full size

Fig. 2. Second-order HOG features of local facial expression image

Download full size

Fig. 3. Structure of DBN

Download full size

Fig. 4. Flowchart of facial expression recognition based on fusion of local features and DBN

Download full size

Fig. 5. Sample images. (a) JAFFE database; (b) CK database; (c) CK+ database

Download full size

Fig. 6. Examples of facial expression database image preprocessing. (a) JAFFE database; (b) CK database; (c) CK+ database

Download full size

Fig. 7. Expression recognition rate of DBN with different RBM layers

Download full size

Table 1. Training and recognition time of DBN with different RBM layers
View table
Table 1. Training and recognition time of DBN with different RBM layers
Database 1 RBMlayer 2 RBMlayers 3 RBMlayers 4 RBMlayers
JAFFE 344.86 228.90 265.38 711.62
CK 337.76 402.75 537.88 669.64
CK+ 369.32 461.98 542.23 743.40

Table 2. Recognition rate based on different features
View table
Table 2. Recognition rate based on different features
Feature JAFFEdatabase CKdatabase CK+database
Gabor 87.96 90.20 88.42
Log-Gabor 93.52 94.77 93.29
HOG 85.19 88.24 86.83
Secondorder HOG 92.59 94.12 92.68
Log-Gabor+Second order HOG 96.30 97.39 95.73

Table 3. Recognition rate of different algorithms%
View table
Table 3. Recognition rate of different algorithms%
Algorithm JAFFEdatabase CKdatabase CK+database
KNN 75.00 78.43 77.44
SVM 82.41 83.01 81.10
DBN 96.30 97.39 95.73

Table 4. Comparison of recognition rate of different methods on JAFFE database
View table
Table 4. Comparison of recognition rate of different methods on JAFFE database
Method Recognition rate /%
PHOG+LBP+SVM^[24] 87.43
Local Gabor+RFLD+KNN^[25] 89.67
LDN+SVM^[26] 90.60
HOG+bagging ELM^[27] 94.37
Proposed method 96.30

Table 5. Comparison of recognition rate of different methods on CK database
View table
Table 5. Comparison of recognition rate of different methods on CK database
Method Recognition rate /%
Local Gabor+RFLD+KNN^[25] 91.51
LBP+MTSL^[28] 91.53
CLBP+SVM^[29] 94.20
GLDPE^[30] 97.08
Proposed method 97.39

Table 6. Comparison of recognition rate of different methods on CK+ database
View table
Table 6. Comparison of recognition rate of different methods on CK+ database
Method Recognitionrate /%
Geometric features+LBP+SVM^[31] 90.08
HOG+DBN+Gabor+SAE^[19] 91.11
PHOG+LBP+SVM^[24] 94.63
Boosted DBN^[20] 96.70
Proposed method 95.73

Tools

Get Citation

Copy Citation Text

Wang Linlin, Liu Jinghao, Fu Xiaomei. Facial Expression Recognition Based on Fusion of Local Features and Deep Belief Network[J]. Laser & Optoelectronics Progress, 2018, 55(1): 11002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites