Abstract
In order to solve the problem of low face recognition rate in controlled scene, an expression recognition algorithm based on residual rectification intensive convolutional neural network is proposed. This method takes convolutional neural network as the prototype. In the process of training model, the idea of residual network is introduced to correct the difference between the effect of test set and the effect of training set. The linear rectification operation of the residual block by the excitation function embedded in the convolution layer helps to express complex features. At the same time, the data intensive method is used to suppress the fast fitting of the deep neural network model during the training process, to improve its generalization performance on a given recognition task, and then to improve the robustness of the model learning effect. In the experiment, the method is applied to simulate the online teaching environment, and get effective facial expression recognition result in controlled scene. According to the experimental data, this method can effectively classify the facial image input under controlled conditions, and the highest accuracy is up to 91.7%. This research is helpful to the development of facial expression recognition and human-computer interaction.
Similar content being viewed by others
References
Barnouti NH, Aldabbagh SSM, Matti WE et al (2016) Face detection and recognition using viola-jones with PCA-LDA and square euclidean distance[J]. Int J Advanc Comp Sci Appl 7(5):371–377
Ekman P, Friesen W. V. Pictures of facial affect//Proceedings of the Consulting Psychologists Press. Palo Alto, USA, 1976: 1–7.
Feifei Z, Tianzhu Z, Qirong M, Changsheng X (2019) Multi-pose facial expression recognition via generative adversarial network[J]. Chin J Comp 42(120):1–16
Goodfellow IJ, Erhan D, Carrier PL et al (2013) Int Conf Neural Inform Process:117–124
Goodfellow, I., Bengio, Y., Courville, A.. Deep learning (Vol. 1). Cambridge:MIT press, 2016:326–366.
Goyal SJ, Upadhyay AK, Jadon RS et al (2018) Real-life facical expression recognition systems: a review[J]. Smart Comput Inform 77(1):311–331
Gu WF, Xiang C, Venkatesh YV et al (2012) Facial expression recognition using radial encoding of local Gabor features and classifier synthesis[J]. Pattern Recogn 45(1):80–91
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, L., Wang, G. and Cai, J., 2015. Recent advances in convolutional neural networks. arXiv preprint arXiv:1512.07108.
Gurovich Y, Hanani Y, Bar O, Nadav G, Fleischer N, Gelbman D, Basel-Salmon L, Krawitz PM, Kamphausen SB, Zenker M, Bird LM, Gripp KW (2019) Identifying facial phenotypes of genetic disorders using deep learning. Nat Med 25(1):60–64
Hongfei L, Qing L, Li Z (2019) Dynamic facial expression recognition based on multi-visual and audio descriptors[J]. Acta Electron Sin 47(8):1643–1653
Jia MX, Du JQ, Song PF et al (2017) Face recognition based on multi-feature optimization fusion of LBP,LPQ and Gabor with multi-scale blocks [J]. J N Univ (Natural Science) 38(3):310–314
Juan L, Hu M, Zhong H (2016) Expression recognition method based on evidence fusion of optimal supportability[J]. J Elec Measur Instrum 30(5):714–721
Kaya H (2017) Gurp?Nar F, Salah a. A. Video-based emotion recognition in the wild using deep transfer learning and score fusion[J]. Image Vis Comput 65:66–75
Lekdioui K, Messoussi (2017) Facial decomposition for expression recognition using texture/shape descriptors and SVM classifier[J]. Signal Process Image Commun 58:300–312
Li Y, Li X, Jiang M (2018) Facial expression recognition based on cross-connect LeNet-5 network[J]. Acta Automat Sin 44(1):176–182
Yao Lisha,Xu Guoming,Zhao Feng. Facial expression recognition based on CNN local feature fusion[J]. Laser Optoelectron Progress,2020,57(03):031501.
Liu YP, Li YB, Ma X et al (2017) Facial expression recognition with fusion features extracted from salient facial areas[J]. Sensors 17(4):712
Lucey P, Cohn J F, Kanade T, et al. The extended cohn-kanade dataset (CK+): A complete dataset for action unit and emotion-specified expression [C]. Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, San Francisco, USA, 2010:94–101.
Mao Q, Zhang F, Wang L, … Dong M (2018) Cascaded multi-level transformed Dirichlet process for multi-pose facial expression recognition[J]. Comput J 61(11):1605–1619
Qianlu H, Qiang W (2019) Facial expression recognition based on cross-connect feature fusion network[J]. Computer Eng Design 31(4):552–559
Soyel H, Demirel H (2012) Localized discriminative scale invariant feature transform based facial expression ecognition[J]. Comp Elec Eng 38(5):1299–1309
Su H, Maji S, Kalogerakis E et al (2015) Multi-view convolutional neural networks for 3d shape recognition//proceedings of the IEEE international conference on computer vision. Santiago, Chile:945–953
Sun X, Pan T (2017) Static facial expression recognition system using ROI deep neural networks[J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica 45(5):1189–1197
Tan X, Li Z, Fan Y (2019) Facial expression recognition method based on multi-scale detail enhancement[J]. J Electron Inform Technol 41(11):2752–2759
Wang XY, Fan JZ, Liu HM et al (2019) Multi-expression sequence fusion recognition based on probabilistic cooperative representation[J]. Laser Optoelectron Progress 56(13):131004
Xia T, Zhang Y, Yuan L (2019) Landmark-based facial expression recognition by joint training of multiple networks[J]. J Comp-Aided Design Comp Graphics 31(4):552–559
Xu Y, Zhenhong S (2020) Facial expression recognition based on improved AlexNet[J]. Laser Optoelectron Progress 57(14):141026
Yao L, Xu G, Zhao F (2020) Facial expression recognition based on CNN local feature fusion[J]. Laser Optoelectron Progress 57(03):031501
Yu HM, Sheng nan, Xiaohua W (2019) Facial expression recognition method based on constraint cycle-consistent generative adversarial networks[J]. J Electron Meas Instrum 33(4):169–177
Zheng W, Zhou X, Zou C, … Zhao L (2006) Facial expression recognition using kernel canonical correlation analysis (KCCA)[J]. IEEE Trans Neural Netw 17(1):233–238
Zheng W, Zhou X, Zou C et al (2006) Facial expression recognition using kernel canonical correlation analysis (KCCA)[J]. IEEE Trans Neural Netw 17(1):233–238
Zhou HL, Kinman L, He XJ (2016) Shape-appearance-correlated active appearance model[J]. Pattern Recogn 56(C):88–99
Funding
Supported by Research on Intelligent Campus of Modern Educational Technology in Jiangsu Province (2021-R-96609).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, B., Zhu, Jn. & Dong, Yz. Expression recognition based on residual rectification convolution neural network. Multimed Tools Appl 81, 9671–9683 (2022). https://doi.org/10.1007/s11042-022-12159-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12159-w