Facial Expression Recognition Based on Improved AlexNet

Xu Yang; Zhenhong Shang

doi:10.3788/LOP57.141026

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 14 >Page 141026 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 14, 141026 (2020)

Facial Expression Recognition Based on Improved AlexNet

Xu Yang and Zhenhong Shang^*

Author Affiliations

Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan 650500, China

show less

DOI: 10.3788/LOP57.141026 Cite this Article Set citation alerts

Xu Yang, Zhenhong Shang. Facial Expression Recognition Based on Improved AlexNet[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141026 Copy Citation Text

show less

Fig. 1. Improved AlexNet network structure

Download full size

Fig. 2. Multi-scale convolutional network structure

Download full size

Fig. 3. Seven facial expressions in the JAFFE database

Download full size

Fig. 4. Seven face expressions in the CK+ database

Download full size

Fig. 5. Data preprocessing process

Download full size

Layer	Net	Input	Convolution size	Stride	Padding	Output
1-1	Convolution1-1	48×48×1	1×1×96	1	Same	48×48×96
1-2	Convolution1-2	48×48×1	3×3×96	1	Same	48×48×96
1-3	Convolution1-3	48×48×1	5×5×96	1	Same	48×48×96
2	Concatenate	-	-	-	-	48×48×288
3	Maxpooling	48×48×288	2×2	2	Valid	24×24×288
4	Convolution	24×24×288	5×5×256	1	Same	24×24×256
5	Maxpooling	24×24×256	2×2	2	Valid	12×12×256
6	Convolution	12×12×256	3×3×384	1	Same	12×12×384
7	Convolution	12×12×384	3×3×384	1	Same	12×12×384
8	Convolution	12×12×384	3×3×256	1	Same	12×12×256
9	Maxpooling	12×12×256	2×2	2	Valid	6×6×256
10	GAP (global average pooling)	24×24×288	-	-	-	288
11	GAP	12×12×256	-	-	-	256
12	Flatten	6×6×256	-	-	-	9216
13	Concatenate	-	-	-	-	9760
14	FC (fully connected layer)	6×6×256	-	-	-	4096
15	FC	4096	-	-	-	4096
16	Softmax	4096	-	-	-	7

Table 1. Parameters of improved AlexNet network

Algorithm	AlexNet	Em-AlexNet
Accuracy of CK+	85.60	94.25
Accuracy of JAFFE	78.57	93.02

Table 2. Comparison of experimental results%

Method	Accuracy
CNN^[5]	81.50
C-LeNet5^[22]	83.74
Local gabor+RFLD+KNN^[23]	91.51
Multi_resolution feature CNN^[24]	92.10
Em-AlexNet	94.25

Table 3. Comparison of different methods in CK+ dataset%

Method	Accuracy
PHOG+LBP+SVM^[25]	87.43
Local gabor+RFLD+KNN^[23]	89.67
LDN+SVM^[26]	90.60
Multi_resolution feature CNN^[24]	91.70
Em-AlexNet	93.02

Table 4. Comparison of different methods in JAFFE dataset%

Method	Surprise	Angry	Contempt	Disgust	Fear	Happy	Sad	Total
AlexNet	96.0	60.0	75.0	100.0	70.0	80.0	85.0	85.6
Em-AlexNet	97.5	96.0	70.0	96.9	91.7	100.0	80.0	94.3

Table 5. Recognition accuracy of AlexNet and Em-AlexNet algorithms for different expressions in the CK+ dataset%

Method	Surprise	Angry	Disgust	Fear	Happy	Neutral	Sad	Total
AlexNet	87.5	62.5	87.5	75.0	75.0	100.0	62.5	78.6
Em-AlexNet	100.0	100.0	100.0	100.0	100.0	100.0	66.7	93.0

Table 6. Recognition accuracy of AlexNet and Em-AlexNet algorithms for different expressions in the JAFFE dataset%

Xu Yang, Zhenhong Shang. Facial Expression Recognition Based on Improved AlexNet[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141026

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information