An Attention Model-Based Facial Expression Recognition Algorithm

Jinghui Chu; Wenhao Tang; Shan Zhang; Wei Lü

doi:10.3788/LOP57.121015

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 12 >Page 121015 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 12, 121015 (2020)

An Attention Model-Based Facial Expression Recognition Algorithm

Jinghui Chu, Wenhao Tang, Shan Zhang, and Wei Lü^*

Author Affiliations

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

show less

DOI: 10.3788/LOP57.121015 Cite this Article Set citation alerts

Jinghui Chu, Wenhao Tang, Shan Zhang, Wei Lü. An Attention Model-Based Facial Expression Recognition Algorithm[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121015 Copy Citation Text

show less

Fig. 1. CSACNN model structure

Download full size

Fig. 2. Channel attention branch

Download full size

Fig. 3. Spatial attention branch

Download full size

Fig. 4. Attention model integration and residual learning unit

Download full size

Fig. 5. 68 face landmarks

Download full size

Fig. 6. Cropping of key areas of facial expression. (a) Original image; (b) facial mask; (c) cropped image

Download full size

Variable	Value	Accuracy /%
	1	97.35
d	4	97.45
	8	97.25
	8	95.72
r	16	97.45
	32	95.41

Table 1. Effect of hyper-parameters on network performance

Dataset	Location	Accuracy /%
	After conv	96.64
CK+	Before pooling	97.45
	After pooling	95.72
	After conv	72.69
MMI	Before pooling	74.73
	After pooling	72.59

Table 2. Effect of attention model location on network performance

Method	Experimentalsetting	Accuracy /%
Method	Experimentalsetting	CK+	MMI
3DCNN^[32]	Sequence-based	85.90	53.20
LBP-TOP^[33]	Sequence-based	88.99	59.51
HOG 3D^[34]	Sequence-based	91.44	60.89
STM-ExpLet^[35]	Sequence-based	94.19	75.12
DTGAN^[18]	Sequence-based	97.25	-
Island Loss^[25]	Image-based	94.39	74.68
IACNN^[22]	Image-based	95.37	71.55
DLPCNN^[24]	Image-based	95.78	-
DeRL^[36]	Image-based	97.30	73.23
Ref.[19]	Image-based	97.37	-
PPDN^[37]	Image-based	97.30	-
VGG16(ours)	Image-based	91.72	64.13
ResNet5(ours)	Image-based	86.87	57.09
CSACNN(ours)	Image-based	97.45	74.73

Table 3. Performance comparison of different expression recognition methods

Model	Accuracy /%
Model	CK+	MMI
Base	94.73	67.61
Base+CA	95.21	71.47
Base+SA	95.62	70.17
Base+Crop	95.82	71.41
Base+CA+SA	96.43	72.98
Base+CA+SA+Crop	97.45	74.73

Table 4. Performance comparison of different modules

Jinghui Chu, Wenhao Tang, Shan Zhang, Wei Lü. An Attention Model-Based Facial Expression Recognition Algorithm[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121015

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information