Research on Facial Expression Recognition Based on the Depthwise
Separable Convolution Structure

Computer & Telecommunication

Current Issue | Archive | Adv Search

Research on Facial Expression Recognition Based on the Depthwise Separable Convolution Structure

Nanjing University of Posts & Telecommunications

Download:

PDF(0KB)
Export: BibTeX | EndNote (RIS)

Abstract Facial expression recognition is an important branch of facial recognition in the field of computer vision. Influenced by many factors including the diversity of facial expressions, changes in head posture and the environment, it is a big challenge to the work of facial expression recognition. Focused on traditional convolutional neural network, owning to its large number of parame- ters and the limited improvement in facial expression recognition accuracy compared with applying traditional machine learning al- gorithms, we proposes an improved convolutional neural network model based on the depthwise separable convolution structure. We make the experiment on the Fer2013 gray expression recognition dataset based on our model, the result shows that the network struc- ture of the model is optimized, the number of model parameters is greatly reduced, and the utilization efficiency of model parame- ters is high, while ensuring a high accuracy rate of 68.31% compared to the traditional convolutional neural network.

Key words： facial expression recognition convolutional neural network depthwise separable convolutions

Published: 17 August 2020

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	JU Cong LI Tao

Cite this article:

JU Cong LI Tao. Research on Facial Expression Recognition Based on the Depthwise Separable Convolution Structure. Computer & Telecommunication, 2020, 1(6): 1-5.

URL:

https://www.computertelecom.com.cn/EN/ OR https://www.computertelecom.com.cn/EN/Y2020/V1/I6/1

[1]	LI Chun-hui WANG Xiao-ying ZHANG Qing-jie LIU Han-zhuo LIANG Jia-ye GAO Ning-kang. DDoS Attack Detection Method Based on Multi-scale Convolutional Neural Network [J]. 电脑与电信, 2024, 1(6): 35-.
[2]	REN Hao. Expression Recognition Method Combined with Attention Feature Fusion[J]. 电脑与电信, 2024, 1(5): 71-.
[3]	WANG Jin WANG Rui. Facial Expression Recognition Algorithm Based on Multi-scale Feature Deep Learning[J]. 电脑与电信, 2024, 1(5): 75-.
[4]	SU Cui-wen CHAI Guo-qiang. Real-time Facial Expression Recognition Based on Facial Feature Detection [J]. 电脑与电信, 2023, 1(1-2): 17-21.
[5]	MA Jin-feng. Facial Expression Recognition Based on Dense Connected Convolution Structure[J]. 电脑与电信, 2021, 1(4): 1-5.
[6]	ZHANG Bao-yan. Research on Geographic Image Classification Based on Deep Convolution Network [J]. 电脑与电信, 2021, 0(10): 75-79.
[7]	ZHANG Gang , CHEN Jia-lian, SONG Jian, GUO Jun-qi, ZHOU Chen-rui. Chinese Landscape Painting Automated Generation Model Based on Generative Adversarial Networks[J]. 电脑与电信, 2020, 1(3): 1-.
[8]	XIE Shumin DENG Lei XIE Zhong-mei LI Hai-ping. DenoisingAlgorithm Based on Convolutional Neural Network in Real Scene[J]. 电脑与电信, 2020, 1(11): 39-43.
[9]	LinWeisheng. The Application of Deep Learning Technologies in Data Analysis of Information System[J]. 电脑与电信, 2017, 1(6): 51-53.
[10]	Li Senlin, Peng Xiaoning. Application of Deep CNN in the Class Status of Students[J]. 电脑与电信, 2017, 1(10): 35-37.

Viewed

Full text

Abstract

Cited

Shared

Discussed