Abstract
With the existence of occlusion or posture changes, facial expression recognition (FER) under uncontrolled conditions is difficult. To obtain a discriminative representation for challenging expression recognition, we present a relation-aware FER model, referred to attention-coordinated contextual residual network (ACRN), which contains a contextual residual network (CRNet) and attention module (AM). Firstly, multi-level features of facial expression are extracted by CRNet. There are some contextual convolution (CoConv) blocks in CRNet to integrate expression information in facial space; then, AM is embedded into each stage of CRNet to coordinate contextual information from CoConv blocks across the channel and spatial location, weighting multi-level expression features to differentiate their importance; finally, to highlight expression-related facial areas, the output of CRNet will be fed into AM, which can focus on salient features. The experiments on Affectnet-7 and RAF_DB datasets have shown that ACRN can both explore the interaction of facial information and capture subtle features related to expression, thus obtaining a better recognition performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ramdani, C., Ogier, M., Coutrot, A.: Communicating and reading emotion with masked faces in the Covid era: a short review of the literature. Psychiat. Res. 316, 114755 (2022)
Deng, S., Sun, Y., Galvan, E.: Neural architecture search using genetic algorithm for facial expression recognition. In: Genetic and Evolutionary Computation Conference Companion, pp. 423–426 (2022)
Seal, A., Saha, R., Kumar, R., et al.: facial emotion recognition in static and live streaming image dataset using CNN. In: International Conference on Computational Intelligence in Communications and Business Analytics, pp. 288–297 (2022)
Tuama, B.A., Shawkat, S.A., Askar, N.A.: Recognition and classification of facial expressions using artificial neural networks. In: 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications, pp. 1–8 (2022)
Yan, R., Yang, M., Zheng, Q., et al.: Facial expression recognition based on hybrid geometry-appearance and dynamic-still feature fusion. Multimedia Tools. Appl. 82, 1–26 (2022)
Lei, J., Liu, Z., Zou, Z., et al.: Mid-level representation enhancement and graph embedded uncertainty suppressing for facial expression recognition. arXiv preprint arXiv: 2207.13235 (2022)
Ramadhan, A.D., Usman, K., Pratiwi, N.K.C.: Comparative analysis of various optimizers on residual network architecture for facial expression identification. In: 2nd International Conference on Electronics, Biomedical Engineering, and Health Informatics, pp. 279–288 (2022)
Ahadit, A.B., Jatoth, R.K.: A novel multi-feature fusion deep neural network using HOG and VGG-Face for facial expression classification. Mach. Vision Appl. 33(4), 1–23 (2022)
Kartheek, M.N., Prasad, M.V.N.K., Bhukya R.: Texture based feature extraction using symbol patterns for facial expression recognition. Cogn. Neurodyn., 1–19 (2022)
Du, Y., Wang, Q., Xiong, Y.: Adaptive graph-based feature normalization for facial expression recognition. arXiv preprint arXiv: 2207.11123 (2022)
Li, Y., Zeng, J., Shan, S., et al.: Patch-gated CNN for occlusion-aware facial expression recognition. In: 24th International Conference on Pattern Recognition, pp. 2209–2214 (2018)
Li, S., Deng, W., Du, J, P.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2852–2861 (2017)
Song, L., Gong, D., Li, Z., et al.: Occlusion robust face recognition based on mask learning with pairwise differential siamese network. In: IEEE/CVF International Conference on Computer Vision, pp. 773–782 (2019)
Xie, S., Hu, H.: Facial expression recognition using hierarchical features with deep comprehensive multipatches aggregation convolutional neural networks. IEEE Trans. Multimedia. 21(1), 211–220 (2018)
Ruan, D., Yan, Y., Lai, S., et al.: Feature decomposition and reconstruction learning for effective facial expression recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7660–7669 (2021)
Zhao, S., Cai, H., Liu, H., et al.: Feature selection mechanism in CNNs for facial expression recognition. In: British Machine Vision Conference, p. 317 (2018)
Huang, Q., Huang, C., Wang, X., et al.: Facial expression recognition with grid-wise attention and visual transformer. Inf. Sci. 580, 35–54 (2021)
Liu, D., Ouyang, X., Xu, S., et al.: SAANet: siamese action-units attention network for improving dynamic facial expression recognition. Neurocomputing 413, 145–157 (2020)
Duta, I.C., Georgescu, M.I., Ionescu, R.T.: Contextual convolutional neural networks. In: IEEE/CVF International Conference on Computer Vision, pp. 403–412 (2021)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713–13722 (2021)
Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18–31 (2017)
Li, S., Deng, W.: Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition. IEEE Trans. Image. Process. 28(1), 356–370 (2018)
Chen, Y., Wang, J., Chen, S., et al.: Facial motion prior networks for facial expression recognition. In: IEEE Visual Communications and Image Processing (VCIP), pp. 1–4 (2019)
Ding, H., Zhou, P., Chellappa, R.: Occlusion-adaptive deep network for robust facial expression recognition. In: IEEE International Joint Conference on Biometrics (IJCB), pp. 1–9 (2020)
Hua, W., Dai, F., Huang, L., et al.: HERO: human emotions recognition for realizing intelligent Internet of Things. IEEE Access 7, 24321–24332 (2019)
Farzaneh, A.H., Qi, X.: Discriminant distribution-agnostic loss for facial expression recognition in the wild. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 406–407 (2020)
Lian, Z., Li, Y., Tao, J.H., et al.: Expression analysis based on face regions in real-world conditions. Int. J. Autom. Comput. 17(1), 96–107 (2020)
Skublov, S.G., Gavrilchik, A.K., Berezin, A.V.: Geochemistry of beryl varieties: comparative analysis and visualization of analytical data by principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE). J. Min. Inst. 255, 455–469 (2022)
Acknowledgment
This work was supported in part by the National Science Foundation of China (Grant No. 61871176), applied research plan of key scientific research projects in Henan colleges and Universities (Grant No. 22A510013), the Scientific Research Foundation Natural Science Project in Henan University of Technology (Grant No. 2018RCJH18), and the Innovative Funds Plan of Henan University of Technology Plan (Grant No. 2020ZKCJ02).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, X., Zhu, C., Zhou, F. (2023). Relation-Aware Facial Expression Recognition Using Contextual Residual Network with Attention Mechanism. In: Hong, W., Weng, Y. (eds) Computer Science and Education. ICCSE 2022. Communications in Computer and Information Science, vol 1811. Springer, Singapore. https://doi.org/10.1007/978-981-99-2443-1_55
Download citation
DOI: https://doi.org/10.1007/978-981-99-2443-1_55
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2442-4
Online ISBN: 978-981-99-2443-1
eBook Packages: Computer ScienceComputer Science (R0)