Facial Expression Recognition Based on Regularized Semi-supervised Deep Learning
In the field of facial expression recognition, deep learning has attracted more and more researchers’ attention as a powerful tool. The method can effectively train and test data by using a neural network. This paper mainly uses the semi-supervised deep learning model for feature extraction and adds a regularized sparse representation model as a classifier. The combination of deep learning features and sparse representations fully exploits the advantages of deep learning in feature learning and the advantages of sparse representation in recognition. Experiments show that the features obtained by deep learning have certain subspace features, which accord with the subspace hypothesis of face recognition based on sparse representation. The method of this paper has a good recognition accuracy in facial expression recognition and has certain advantages in small sample problems.
KeywordsSemi-supervised learning Regularization Facial expression recognition Deep learning
This paper is supported by Jilin Provincial Education Department “13th five-year” Science, Technology Project (No. JJKH20170571KJ), National Natural Science Foundation of China under Grant 61873304, The Science & Technology Plan Project Changchun City under Grant No. 17SS012, and the Industrial Innovation Special Funds Project of Jilin Province under Grant No. 2018C038-2 & 2019C010.
- 1.Weston, J., Ratle, F., Mobahi, H., et al.: Deep learning via semi-supervised embedding. Neural Networks: Tricks of the Trade, pp. 639–655. Springer, Berlin, Heidelberg (2012)Google Scholar
- 2.Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 2 (2013)Google Scholar
- 3.Huang, K., Aviyente, S.: Sparse representation for signal classification. Advances in Neural Information Processing Systems, pp. 609–616 (2007)Google Scholar
- 4.Lee, K.C., Ho, J., Kriegman, D.J.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. Pattern Anal. Mach. Intell. 5, 684–698 (2005)Google Scholar
- 6.Yang, M., Zhang, L., Feng, X., et al.: Fisher discrimination dictionary learning for sparse representation. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 543–550. IEEE (2011)Google Scholar
- 11.Guo, Y., Tao, D., Yu, J., et al.: Deep neural networks with relativity learning for facial expression recognition. In: 2016 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 1–6. IEEE (2016)Google Scholar