10. Improving accuracy in facial emotion recognition through PCA and Artificial Neural Networks
DOI:
https://doi.org/10.61591/jslhu.26.956Từ khóa:
Facial emotion recognition; Principal Component Analysis; Artificial Neural Network; Feature extraction; Emotion classification.Tóm tắt
This study presents a facial emotion recognition approach based on Principal Component Analysis (PCA) and Artificial Neural Networks (ANN). The proposed pipeline includes facial-image preprocessing, PCA-based feature extraction, and ANN-based emotion classification on the JAFFE and FEI datasets. The main objective of the study is to evaluate the effect of hidden-neuron size on classification accuracy under the same preprocessing and feature-extraction pipeline. Experimental results show that the PCA-ANN model achieves the highest accuracy of 96.3% on the JAFFE dataset with 40 hidden neurons and 97.0% on the FEI dataset with 5 hidden neurons. These findings indicate that hidden-layer size is an influential design parameter in PCA-ANN-based facial emotion recognition and that suitable hidden-neuron settings differ across datasets. The proposed method offers a lightweight structure, low computational cost, and practical suitability for small and controlled datasets. In future work, the framework can be extended to more diverse datasets and more challenging emotion configurations in order to examine its generalizability more thoroughly.
Tài liệu tham khảo
Jayaswal, R., Ansari, M. A., Dixit, M., Singh, D. K., & Ahmad, S. (2025). Advances in facial expression recognition technologies for emotion analysis. Discover Computing, 28, 203. https://doi.org/10.1007/s10791-025-09699-8.
Sajjad, M., Ullah, F. U. M., Ullah, M., Christodoulou, G., Cheikh, F. A., Hijji, M., Muhammad, K., & Rodrigues, J. J. P. C. (2023). A comprehensive survey on deep facial expression recognition: challenges, applications, and future guidelines. Alexandria Engineering Journal, 68, 817-840. https://doi.org/10.1016/j.aej.2023.01.017.
Kopalidis, T., Solachidis, V., Vretos, N., & Daras, P. (2024). Advances in Facial Expression Recognition: A Survey of Methods, Benchmarks, Models, and Datasets. Information, 15(3), 135. https://doi.org/10.3390/info15030135.
Huang, Z.-Y., Chiang, C.-C., Chen, J.-H., Chen, Y.-C., Chung, H.-L., Cai, Y.-P., & Hsu, H.-C. (2023). A study on computer vision for facial emotion recognition. Scientific Reports, 13, 8425. https://doi.org/10.1038/s41598-023-35446-4.
Elsheikh, R. A., Mohamed, M. A., Abou-Taleb, A. M., & Ata, M. M. (2024). Improved facial emotion recognition model based on a novel deep convolutional structure. Scientific Reports, 14, 29050. https://doi.org/10.1038/s41598-024-79167-8.
Yaddaden, Y. (2023). An efficient facial expression recognition system with appearance-based fused descriptors. Intelligent Systems with Applications, 17, 200166. https://doi.org/10.1016/j.iswa.2022.200166.
Liu, C., Hirota, K., Ma, J., Jia, Z., & Dai, Y. (2021). Facial Expression Recognition Using Hybrid Features of Pixel and Geometry. IEEE Access, 9, 18876-18889. https://doi.org/10.1109/ACCESS.2021.3054332.
Kim, J.-C., Kim, M.-H., Suh, H.-E., Naseem, M. T., & Lee, C.-S. (2022). Hybrid Approach for Facial Expression Recognition Using Convolutional Neural Networks and SVM. Applied Sciences, 12(11), 5493. https://doi.org/10.3390/app12115493.
Tang, X., Feng, J., Huang, J., Xiang, Q., & Xue, B. (2024). A lightweight and continuous dimensional emotion analysis system of facial expression recognition under complex background. Journal of Visual Communication and Image Representation, 103, 104260. https://doi.org/10.1016/j.jvcir.2024.104260.
Barman, A., & Dutta, P. (2024). Facial expression recognition using Reversible Neural Network. Applied Soft Computing, 162, 111815. https://doi.org/10.1016/j.asoc.2024.111815.
Thomaz, C. E., & Giraldi, G. A. (2024). Dataset: FEI dataset for face recognition. https://doi.org/10.57702/ahg4qnqc.
