EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DA-FER: Domain Adaptive Facial Expression Recognition

Mei Bie, Huan Xu, Quanle Liu, Yan Gao, Kai Song, Xiangjiu Che

Applied Sciences · 22.05.2023 · 13 (10) · 6314

DOI: 10.3390/app13106314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.05.2023. Verfasst von Mei Bie und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Development Plan of Jilin Province of China, Social Science Research of the Education Department of Jilin Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Facial expression recognition (FER) is an important field in computer vision with many practical applications. However, one of the challenges in FER is dealing with small sample data, where the number of samples available for training machine learning algorithms is limited. To address this issue, a domain adaptive learning strategy is proposed in this paper. The approach uses a public dataset with sufficient samples as the source domain and a small sample dataset as the target domain. Furthermore, the maximum mean discrepancy with kernel mean embedding is utilized to reduce the disparity between the source and target domain data samples, thereby enhancing expression recognition accuracy. The proposed Domain Adaptive Facial Expression Recognition (DA-FER) method integrates the SSPP module and Slice module to fuse expression features of different dimensions. Moreover, this method retains the regions of interest of the five senses to accomplish more discriminative feature extraction and improve the transfer learning capability of the network. Experimental results indicate that the proposed method can effectively enhance the performance of expression recognition. Specifically, when the self-collected Selfie-Expression dataset is used as the target domain, and the public datasets RAF-DB and Fer2013 are used as the source domain, the performance of expression recognition is improved to varying degrees, which demonstrates the effectiveness of this domain adaptive method.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Development Plan of Jilin Province of China
  • Social Science Research of the Education Department of Jilin Province
  • Jilin Educational Scientific Research Leading Group
  • Humanities and Social Science Foundation of Changchun Normal University

Zitieren

APA

Bie, M., Xu, H., Liu, Q., Gao, Y., Song, K., & Che, X. (2023). DA-FER: Domain Adaptive Facial Expression Recognition. Applied Sciences, 13(10), 6314. https://doi.org/10.3390/app13106314

Vancouver

Bie M, Xu H, Liu Q, Gao Y, Song K, Che X. DA-FER: Domain Adaptive Facial Expression Recognition. Applied Sciences. 2023;13(10):6314. doi:10.3390/app13106314

BibTeX
@article{Bie2023,
  author = {Bie, Mei and Xu, Huan and Liu, Quanle and Gao, Yan and Song, Kai and Che, Xiangjiu},
  title = {DA-FER: Domain Adaptive Facial Expression Recognition},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {10},
  pages = {6314},
  doi = {10.3390/app13106314}
}
Kostenlos starten →