Micro-Expression Recognition Algorithm Based on Multiple Motive Feature Fusion

Fig. 3. Diagram of optical flow and optical strain. (a) Start frame of micro-expression; (b) peak frame of micro-expression;(c) optical flow visualization image; (d) optical strain visualization image

Download full size

Table 1. Performance comparison of different data in CNN module
View table
Table 1. Performance comparison of different data in CNN module
Input data Accuracy /%
Optical strain 47.98
LMF 45.70
Optical flow 41.50
Original data 36.65

Table 2. Result comparison of single feature map and multiple feature fusion map
View table
Table 2. Result comparison of single feature map and multiple feature fusion map
ExperimentNo. Opticalstrain LMF Opticalflow Accuracy /%
1 √ 52.45
2 √ 51.38
3 √ 50.54
4 √ √ √ 58.53

Table 3. Comparison of indicators of different algorithms

View table

Table 3. Comparison of indicators of different algorithms

Algorithm	Accuracy /%	UAR /%	F1-score /%
LBP-TOP^*	45.95	30.94	29.41
LBP-SIP^r	46.56		44.80
FDM^o	45.93		40.53
ELRCN-TE^*	50.00	39.37	43.4
MRW^o	46.15		43.07
STCLQP^o	58.39		58.36
MDMO^r	44.25		44.16
Bi-WOOF^o	57.89		61.25
Proposed algorithm	58.53	48.07	52.82

Tools

Get Citation

Copy Citation Text

Yuting Su, Mengmeng Wang, Jing Liu, Yunpeng Fei, Xu He. Micro-Expression Recognition Algorithm Based on Multiple Motive Feature Fusion[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141504

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites