App. Res. of Comp. Accepted Paper
Vol. 39, 2022 No. 8

Research on lightweight facial expression recognition based on label distribution learning

Liu Jin1
Luo Xiaoshu1
Xu Zhaoxing2
1. School of Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541000, China
2. School of Big Data, Jiangxi Institute of Clothing University, Nanchang Jiangxi 330000, China
DOI: 10.19734/j.issn.1001-3695.2021.12.0697

Abstract

Aiming at the problems of insufficient facial expression feature extraction in complex environments, insufficient generalization ability, and single-label data sets that cannot effectively describe the ambiguous expressions caused by complex emotional tendencies, this paper proposed a facial expression recognition method combining improved ShuffleNet and label distribution learning. On the premise of not greatly increasing the computational complexity, to avoid over-fitting of the model, designed a new output module to improve the ShuffleNet; to enhance the model's ability to extract important local details of facial expression images, designed a parallel depthwise convolution residual module to realize the fusion of local and global features. In order to reduce the negative impact of ambiguous expressions on recognition performance, used the label distribution learning method to make full use of the original information of the data set to generate the label distribution without introducing additional information and retrain the improved ShuffleNet model. The experimental results show that the accuracy rates of 87.15%, 62.05% and 58.49% are achieved on the facial expression data sets RAF-DB, AffectNet-7 and AffectNet-8, at the same time, the number of parameters and FLOPs are kept at a low level, which is conducive to its application in actual production.

Foundation Support

广西人文社会科学发展研究中心科学研究工程•创新创业专项(重大委托项目)(ZDCXCY01)
广西自然科学基金资助项目(2018GXNSFAA281351)
广西科技重大专项(桂科AA18118004)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2021.12.0697
Publish at: Application Research of Computers Accepted Paper, Vol. 39, 2022 No. 8

Publish History

[2022-03-15] Accepted Paper

Cite This Article

刘劲, 罗晓曙, 徐照兴. 基于标签分布学习的轻量级人脸表情识别研究 [J]. 计算机应用研究, 2022, 39 (8). (). https://doi.org/10.19734/j.issn.1001-3695.2021.12.0697. (Liu Jin, Luo Xiaoshu, Xu Zhaoxing. Research on lightweight facial expression recognition based on label distribution learning [J]. Application Research of Computers, 2022, 39 (8). (). https://doi.org/10.19734/j.issn.1001-3695.2021.12.0697. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)