Abstract
In this paper, an improved model based on the combination of residual and inverted residual blocks is proposed for image expression recognition, named as bi-directional residual network. The main objective of the proposed method is to alleviate the problem of feature dispersion due to the deep network level in traditional expression recognition research. In this case, residual block is a good solution. However, residual network with small scale of training data can easily lead to over-fitting, which is often the case for image expression recognition. To improve the robustness of the network during training, inverted residual blocks are therefore adopted. Depending on the organization sequence of residual blocks and inverted residual blocks, three network structures are proposed and studied. Fer2013 and CK+ datasets in facial field are adopted for experiment. The experimental results show that the optimized algorithm improves the accuracy by 2.79% on Fer2013 dataset compared with ResNet-50 models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akiba, T., Suzuki, S., Fukuda, K.: Extremely large minibatch SGD: training ResNet-50 on ImageNet in 15 minutes (2017)
Balduzzi, D., Frean, M., Leary, L., Lewis, J.P., Mcwilliams, B.: The shattered gradients problem: if ResNets are the answer, then what is the question? (2017)
Barsoum, E., Zhang, C., Ferrer, C.C., Zhang, Z.: Training deep networks for facial expression recognition with crowd-sourced label distribution. In: ACM International Conference on Multimodal Interaction (2016)
Bengio, Y.: Knowledge matters: importance of prior information for optimization (2016)
Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks (2017)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision Pattern Recognition (2017)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks, pp. 249–256 (2010)
Gu, W., Xiang, C., Venkatesh, Y.V., Huang, D., Lin, H.: Facial expression recognition using radial encoding of local Gabor features and classifier synthesis. Pattern Recogn. 45(1), 80–91 (2012)
Guan-Ming, L.U., Guo, M., Xiao-Nan, L.I., Hai-Bo, L.I.: Recognition for expression of pain in neonate using support vector machine. J. Nanjing Univ. Posts Telecommun. 25(3), 582–587 (2008)
Guan-Ming, L.U., Zuo, J.K.: Feature extraction based on two-dimensional locality preserving discriminant analysis. J. Nanjing Univ. Posts Telecommun. (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015)
Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Matthews, I.: The extended Cohn-Kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: Computer Vision Pattern Recognition Workshops (2010)
Mehrabian, A.: Communication without words. Commun. Theory 6, 193–200 (2008)
Mollahosseini, A., Chan, D., Mahoor, M.H.: Going deeper in facial expression recognition using deep neural networks. In: IEEE Winter Conference on Applications of Computer Vision (2016)
Orhan, A.E., Pitkow, X.: Skip connections eliminate singularities (2017)
Ping, L., Han, S., Meng, Z., Yan, T.: Facial expression recognition via a boosted deep belief network. In: IEEE Conference on Computer Vision Pattern Recognition (2014)
Rusiecki, A.: Trimmed categorical cross-entropy for deep learning with label noise. Electron. Lett. 55(6), 319–320 (2019)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks (2018)
Shan, C., Gong, S., Mcowan, P.W.: Facial expression recognition based on local binary patterns: a comprehensive study. Image Vis. Comput. 27(6), 803–816 (2009)
Shan, L., Deng, W.: Deep facial expression recognition: a survey (2018)
Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-ResNet and the impact of residual connections on learning (2016)
Wang, X., Chao, J., Wei, L., Min, H., Ren, F.: Feature fusion of HOG and WLD for facial expression recognition. In: IEEE/SICE International Symposium on System Integration (2013)
Wu, Z., Shen, C., Van Den Hengel, A.: Wider or deeper: revisiting the ResNet model for visual recognition, vol. 90 (2016)
Yang, H., Ciftci, U., Yin, L.: Facial expression recognition by de-expression residue learning. Int. J. Comput. Sci. Eng. (2018)
Yu, Z., Zhang, C.: Image based static facial expression recognition with multiple deep network learning. In: ACM on International Conference on Multimodal Interaction (2015)
Acknowledgement
The study was supported by the Major Project of Natural Science Research of the Jiangsu Higher Education Institutions of China (18KJA520012), and the Xuzhou Science and Technology Plan Project (KC19197).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Jiang, D., Zhang, S., Yu, C., Tian, C. (2021). A Bi-directional Residual Network for Image Expression Recognition. In: Song, H., Jiang, D. (eds) Simulation Tools and Techniques. SIMUtools 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 369. Springer, Cham. https://doi.org/10.1007/978-3-030-72792-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-72792-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72791-8
Online ISBN: 978-3-030-72792-5
eBook Packages: Computer ScienceComputer Science (R0)