The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
The Influence of the Activation Function in a Convolution Neural Network Model of Facial Expression Recognition
Open accessAbstract
The convolutional neural network (CNN) has been widely used in image recognition field due to its good performance. This paper proposes a facial expression recognition method based on the CNN model. Regarding the complexity of the hierarchic structure of the CNN model, the activation function is its core, because the nonlinear ability of the activation function really makes the deep neural network have authentic artificial intelligence. Among common activation functions, the ReLu function is one of the best of them, but it also has some shortcomings. Since the derivative of the ReLu function is always zero when the input value is negative, it is likely to appear as the phenomenon of neuronal necrosis. In order to solve the above problem, the influence of the activation function in the CNN model is studied in this paper. According to the design principle of the activation function in CNN model, a new piecewise activation function is proposed. Five common activation functions (i.e., sigmoid, tanh, ReLu, leaky ReLus and softplus–ReLu, plus the new activation function) have been analysed and compared in facial expression recognition tasks based on the Keras framework. The Experimental results on two public facial expression databases (i.e., JAFFE and FER2013) show that the convolutional neural network based on the improved activation function has a better performance than most-of-the-art activation functions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Facial expression recognition based on Local Binary Patterns: A comprehensive study
Shan, C., Gong, S., & McOwan, P. W. (2009) · Image and Vision Computing · doi:10.1016/j.imavis.2008.08.005 · Cited by 2,300
Greenspan, H., van Ginneken, B., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2553401 · Cited by 1,700
Extreme Learning Machine for Multilayer Perceptron
Tang, J., Deng, C., & Huang, G.-B. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2424995 · Cited by 1,451
Affective Computing and Sentiment Analysis
Cambria, E. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.31 · Cited by 1,204
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
Wang, K., Peng, X., Yang, J., Meng, D., & Qiao, Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2956143 · Cited by 940
Lopes, A. T., de Aguiar, E., De Souza, A. F., & Oliveira-Santos, T. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.07.026 · Cited by 799
Sequential Deep Learning for Human Action Recognition
Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., & Baskurt, A. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-25446-8_4 · Cited by 782
Facial Expression Recognition via a Boosted Deep Belief Network
Liu, P., Han, S., Meng, Z., & Tong, Y. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.233 · Cited by 650
Fusing audio, visual and textual clues for sentiment analysis from multimodal content
Poria, S., Cambria, E., Howard, N., Huang, G.-B., & Hussain, A. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.01.095 · Cited by 534 · cited 1×
“[6] proposed a novel methodology for multimodal sentiment analysis, and this method consisted of harvesting sentiments from Web videos.”
MethodNg, W., Minasny, B., Montazerolghaem, M., Padarian, J., Ferguson, R., Bailey, S., & McBratney, A. B. (2019) · Geoderma · doi:10.1016/j.geoderma.2019.06.016 · Cited by 466
Mahdianpari, M., Salehi, B., Rezaee, M., Mohammadimanesh, F., & Zhang, Y. (2018) · Remote Sensing · doi:10.3390/rs10071119 · Cited by 440
A comparison of deep networks with ReLU activation function and linear spline-type methods
Eckle, K., & Schmidt-Hieber, J. (2019) · Neural Networks · doi:10.1016/j.neunet.2018.11.005 · Cited by 409
Fashioning the face: sensorimotor simulation contributes to facial expression recognition
Wood, A., Rychlowska, M., Korb, S., & Niedenthal, P. (2016) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2015.12.010 · Cited by 353
Akcay, S., Kundegorski, M. E., Devereux, M., & Breckon, T. P. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532519 · Cited by 299
Agrawal, A., & Mittal, N. (2020) · The Visual Computer · doi:10.1007/s00371-019-01630-9 · Cited by 293
Comparative Study of Convolution Neural Network’s Relu and Leaky-Relu Activation Functions
Dubey, A. K., & Jain, V. (2019) · Lecture Notes in Electrical Engineering · doi:10.1007/978-981-13-6772-4_76 · Cited by 278
Japanese Female Facial Expression (JAFFE) Database
Lyons, M. J., Kamachi, M., & Gyoba, J. (2017) · Figshare · doi:10.6084/m9.figshare.5245003 · Cited by 226
Fuzzy commonsense reasoning for multimodal sentiment analysis
Chaturvedi, I., Satapathy, R., Cavallari, S., & Cambria, E. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.04.024 · Cited by 170
Deep learning for source camera identification on mobile devices
Freire-Obregón, D., Narducci, F., Barra, S., & Castrillón-Santana, M. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.01.005 · Cited by 149
Baseline CNN structure analysis for facial expression recognition
Shin, M., Kim, M., & Kwon, D. (2016) · IEEE RO-MAN · doi:10.1109/roman.2016.7745199 · Cited by 95
Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network
Hou, S., & Wang, Z. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018425 · Cited by 85
Bawa, V. S., & Kumar, V. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.11.042 · Cited by 60
Performance surfaces of a single-layer perceptron
Shynk, J. J. (1990) · IEEE Transactions on Neural Networks · doi:10.1109/72.80252 · Cited by 58
A novel non-linear modifier for adaptive illumination normalization for robust face recognition
Vishwakarma, V. P., & Dalal, S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08537-6 · Cited by 47
Research on a learning rate with energy index in deep learning
Zhao, H., Liu, F., Zhang, H., & Liang, Z. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.12.009 · Cited by 41
Deep Learning for Biometric Face Recognition: Experimental Study on Benchmark Data Sets
Selitskaya, N., Sielicki, S., Jakaite, L., Schetinin, V., Evans, F., Conrad, M., & Sant, P. (2020) · Unsupervised and semi-supervised learning · doi:10.1007/978-3-030-32583-1_5 · Cited by 14
Multi-view Cooperative Deep Convolutional Network for Facial Recognition with Small Samples Learning
Alfakih, A., Yang, S., & Hu, T. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-23887-2_24 · Cited by 9
Lohani, H. K., Dhanalakshmi, S., & Hemalatha, V. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-0617-4_59 · Cited by 6
Prediction of vehicle casualties in major traffic accidents based on neural network
Yang, J., Duan, A., Li, K., et al. (2019) · AIP conference proceedings · doi:10.1063/1.5090752 · Cited by 6
Nandi, A., Dutta, P., & Nasir, M. (2020) · Studies in computational intelligence · doi:10.1007/978-981-15-1041-0_9 · Cited by 5
Cited by
Activation functions in deep learning: a comprehensive survey and benchmark
Dubey, S. R., Singh, S. K., & Chaudhuri, B. B. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.111 · Cited by 1,259
Manoharan, A., Begam, K. M., Aparow, V. R., & Sooriamoorthy, D. (2022) · Journal of Energy Storage · doi:10.1016/j.est.2022.105384 · Cited by 293
Metadata
- Authors
- Wang, Y., Li, Y., Song, Y., & Rong, X.
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2020-03-10
- Volume
- 10
- Issue
- 5
- Pages
- 1897
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W3012334084
- Cited by
- 320
- References
- 30
- FWCI
- 49.50
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.