Comparison of CNN-Based Models in Facial Micro-Expression Classification
DOI:
https://doi.org/10.54097/bkbs9y68Keywords:
Facial Expression; Deep Learning; CNNs; VGG.Abstract
With the rapid development of deep learning, especially the application of Convolutional Neural Networks (CNNs), significant progress has been made in the identification and recognition of facial micro-expressions. This paper explores and compares three widely used models in this field: VGG, DenseNet, and ResNet, across seven expression labels—Anger, Disgust, Fear, Happiness, Neutral, Sadness, and Surprise. The comparison is based on several key evaluation metrics commonly used in deep learning classification tasks. To ensure consistency, critical training parameters such as epochs, learning rate, and data preprocessing steps are kept the same across all models. Additionally, a dropout layer is incorporated to address issues such as overfitting and improve generalization in each model. These works indicate that VGG has the highest performance in RAFDB dataset because it as an F1-score of 0.76, an AUC value of 0.95, and a 75% accuracy rate. Additionally, VGG uses only 1243.31MB of memory, making it the most efficient model compared to the other two models. This shows that VGG excels not only in performance but also in memory efficiency.
Downloads
References
[1] Zhao G, Li X, Li Y, et al. Facial Micro-expressions: an overview[J]. Proceedings of the IEEE, 2023, 111(10): 1215-1235. DOI: https://doi.org/10.1109/JPROC.2023.3275192
[2] Mellouk, W. and Handouzi, W. (2020). Facial emotion recognition using deep learning: review and insights. Procedia Computer Science, 175, 689-694 DOI: https://doi.org/10.1016/j.procs.2020.07.101
[3] Chen Z, Ansari R, Wilkie D. Automated pain detection from facial expressions using facs: A review[J]. arXiv preprint arXiv:1811.07988, 2018.
[4] Sharifani K, Amini M. Machine learning and deep learning: A review of methods and applications[J]. World Information Technology and Engineering Journal, 2023, 10(07): 3897-3904.
[5] Zeng X, Zhao X, Zhong X, et al. A survey of micro-expression recognition methods based on lbp, optical flow and deep learning[J]. Neural Processing Letters, 2023, 55(5): 5995-6026. DOI: https://doi.org/10.1007/s11063-022-11123-x
[6] Bargshady, G., Zhou, X., Deo, R. C., Soar, J., Whittaker, F. and Wang, H. (2020). Enhanced deep learning algorithm development to detect pain intensity from facial expression images. Expert Systems with Applications, 149, 113305 DOI: https://doi.org/10.1016/j.eswa.2020.113305
[7] Fei, Z., Yang, E., Li, D. D.-U., Butler, S., Ijomah, W., Li, X., et al. (2020). Deep convolution network-based emotion analysis towards mental health care. Neurocomputing, 388, 212-227, 2020 DOI: https://doi.org/10.1016/j.neucom.2020.01.034
[8] Zeiler M D, Fergus R. Visualizing and understanding convolutional networks[C]//Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13. Springer International Publishing, 2014: 818-833. DOI: https://doi.org/10.1007/978-3-319-10590-1_53
[9] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[10] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. [J]. CoRR,2014, abs/1409.1556
[11] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708. DOI: https://doi.org/10.1109/CVPR.2017.243
[12] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778. DOI: https://doi.org/10.1109/CVPR.2016.90
[13] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The journal of machine learning research, 2014, 15(1): 1929-1958.
[14] Das A, Jalal M S, Bari A S M S, et al. Facial Emotion Recognition by Ensemble-DenseNet Networks[C]//2023 IEEE 11th Region 10 Humanitarian Technology Conference (R10-HTC). IEEE, 2023: 608-613. DOI: https://doi.org/10.1109/R10-HTC57504.2023.10461880
[15] Tang J, Su Q, Su B, et al. Parallel ensemble learning of convolutional neural networks and local binary patterns for face recognition[J]. Computer Methods and Programs in Biomedicine, 2020, 197: 105622. DOI: https://doi.org/10.1016/j.cmpb.2020.105622
[16] Liu H, Cai H, Lin Q, et al. Adaptive multilayer perceptual attention network for facial expression recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(9): 6253-6266. DOI: https://doi.org/10.1109/TCSVT.2022.3165321
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
