CNN-Based Facial Expression Recognition with Simultaneous Consideration of Inter-Class and Intra-Class Variations
Author:
Pham Trong-Dong1, Duong Minh-Thien1ORCID, Ho Quoc-Thien1, Lee Seongsoo2ORCID, Hong Min-Cheol3ORCID
Affiliation:
1. Department of Information and Telecommunication Engineering, Soongsil University, Seoul 06978, Republic of Korea 2. Department of Intelligent Semiconductor, Soongsil University, Seoul 06978, Republic of Korea 3. School of Electronic Engineering, Soongsil University, Seoul 06978, Republic of Korea
Abstract
Facial expression recognition is crucial for understanding human emotions and nonverbal communication. With the growing prevalence of facial recognition technology and its various applications, accurate and efficient facial expression recognition has become a significant research area. However, most previous methods have focused on designing unique deep-learning architectures while overlooking the loss function. This study presents a new loss function that allows simultaneous consideration of inter- and intra-class variations to be applied to CNN architecture for facial expression recognition. More concretely, this loss function reduces the intra-class variations by minimizing the distances between the deep features and their corresponding class centers. It also increases the inter-class variations by maximizing the distances between deep features and their non-corresponding class centers, and the distances between different class centers. Numerical results from several benchmark facial expression databases, such as Cohn-Kanade Plus, Oulu-Casia, MMI, and FER2013, are provided to prove the capability of the proposed loss function compared with existing ones.
Funder
Korean Government, Ministry of Trade, Industry and Energy Industrial Technology Challenge Track of MOTIE/Korea Evaluation Institute of Industrial Technology Research and Development Program of MOTIE
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference48 articles.
1. Jourabloo, A., De la Torre, F., Saragih, J., Wei, S.E., Lombardi, S., Wang, T.L., Belko, D., Trimble, A., and Badino, H. (2022, January 18–24). Robust egocentric photo-realistic facial expression transfer for virtual reality. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. 2. A Fast CPU Real-Time Facial Expression Detector Using Sequential Attention Network for Human–Robot Interaction;Putro;IEEE Trans. Ind. Inf.,2022 3. Xiao, H., Li, W., Zeng, G., Wu, Y., Xue, J., Zhang, J., Li, C., and Guo, G. (2022). On-road driver emotion recognition using facial expression. Appl. Sci., 12. 4. Farkhod, A., Abdusalomov, A.B., Mukhiddinov, M., and Cho, Y.I. (2022). Development of Real-Time Landmark-Based Emotion Recognition CNN for Masked Faces. Sensors, 22. 5. Dynamic texture recognition using local binary patterns with an application to facial expressions;Zhao;IEEE Trans. Pattern Anal. Mach. Intell.,2007
|
|