Performance Comparison of Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) Algorithms in Human Face Classification
DOI:
https://doi.org/10.70609/g-tech.v9i3.7384Keywords:
Facial Recognition, CNN, SVM, Stress Classification, Deep LearningAbstract
Facial expression recognition is crucial in fields like mental health monitoring and human-computer interaction. This study compares Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) in classifying facial images into stress and non-stress categories. Using a preprocessed dataset of labeled facial expressions, CNN was employed for its strength in automatic spatial feature extraction, while SVM served as a traditional machine learning benchmark. Both models were trained and tested on the same dataset split. Results showed CNN outperformed SVM in all performance metrics: CNN achieved 88.94% accuracy, 94.42% precision, 93.25% recall, and an F1-score of 89.85%, while SVM recorded 76.53% accuracy, 77.14% precision, 85.72% recall, and an F1-score of 80.67%. Despite its lower performance, SVM had faster training and a simpler structure, making it suitable for resource-limited scenarios. The study emphasizes the superiority of deep learning for complex image classification tasks.
References
Ahmed, F., Bari, H., & Hossain, E. (2021). Facial expression recognition using convolutional neural network with data augmentation. Procedia Computer Science, 179, 703–710. https://doi.org/10.1016/j.procs.2020.12.089.
Al-Shabi, M. (2020). Facial expression recognition via deep learning. Journal of Physics: Conference Series, 1432(1), 012059. https://doi.org/10.1088/1742-6596/1432/1/012059.
Aouani, H., & Ben Ayed, Y. (2024). Deep facial expression detection using Viola–Jones algorithm, CNN MLP and CNN SVM. Social Network Analysis and Mining, 14, 65. https://doi.org/10.1007/s13278 024 01231 y
Astuti, P. D., Hartati, S., & Lestari, D. P. (2021). Implementasi Convolutional Neural Network untuk klasifikasi ekspresi wajah menggunakan dataset KDEF. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 5(3), 502–508. https://doi.org/10.29207/resti.v5i3.2931.
Chen, J., Liu, H., & Zhang, Y. (2022). A hybrid CNN-SVM model for facial expression recognition. Multimedia Tools and Applications, 81, 30745–30760. https://doi.org/10.1007/s11042-022-12883-5.
Choirina, P., Huda, M. M., Jannah, U. M., Utama, S., & Pradani, E. R. K. (2021). Pelatihan Topologi Jaringan Menggunakan Cisco Packet Tracer untuk Meningkatkan Kompetensi Mahasiswa Politeknik Angkatan Darat Malang. Mitra Mahajana: Jurnal Pengabdian Masyarakat, 2(2), 117–123.
Ghimire, D., & Lee, J. (2020). Deep learning-based facial expression recognition using hybrid features. Sensors, 20(23), 6674. https://doi.org/10.3390/s20236674.
Gong, Z., Wang, H., & Li, H. (2022). Multi-feature fusion and CNN-based facial expression recognition. Sensors, 22(3), 1047. https://doi.org/10.3390/s22031047.
Harrabi, R., Ben Chaabane, S. E., & Seddik, H. (2025). Hybrid approach for face recognition using CNN, fuzzy logic, and SVM classifier. Preprints.org. https://doi.org/10.3390/preprints2025012292
Hebri, D., Nuthakki, R., & Digal, A. (2024). Effective facial expression recognition system using machine learning. Journal of Ambient Intelligence and Humanized Computing, 15, 1819–1830. https://doi.org/10.1007/s41870 023 01183 0
Hosseini, M., Bodaghi, M., & Bhupatiraju, R. T. (2023). Multimodal stress detection using facial landmarks and biometric signals. arXiv. https://doi.org/10.48550/arXiv.2311.03606
Indu, S. S., Harshendra, M., & Kishore, K. B. (2025). Real time stress detection using deep learning with facial expressions and vocal signals. International Research Journal of Education and Technology, 8(4), 1173–1185.
Jayasree, T., & Thenmozhi, K. (2025). Stress detection based on facial expression. International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, 13(3), 317–324. https://doi.org/10.17148/IJIREEICE.2025.13354
Kishore, G. D. K. K., Prasanna, K., & Vijay Kumar, K. (2025). Real time human facial expression and stress recognition using CNN. International Journal of Creative Research Thoughts, 13(4), 1–11.
Kumar, A., Verma, B., & Singh, R. (2022). Emotion recognition using facial expressions based on deep convolutional neural networks. Journal of Intelligent & Fuzzy Systems, 43(3), 2853–2863. https://doi.org/10.3233/JIFS-219229.
Kumar, G. S., Cheriyan, J., & Aparna, N. (2025). Unleashing facial expression recognition for stress detection using deep CNN model. Procedia Computer Science, 259(1), 306–315. https://doi.org/10.1016/j.procs.2025.03.332
Mahapatra, S., & Panda, S. (2020). Comparative study of facial emotion detection using SVM and CNN. International Journal of Scientific & Technology Research, 9(4), 2897–2900.
Putri, N. L., & Rahmat, R. F. (2023). Performance analysis of CNN and SVM for facial expression recognition using KDEF dataset. Journal of Computer Science and Information, 16(1), 19–26. https://doi.org/10.21609/jiki.v16i1.1356.
Wang, Y., Wu, Q., & Ji, Q. (2021). Real-time facial expression recognition with CNNs using KDEF dataset. Pattern Recognition Letters, 146, 1–7. https://doi.org/10.1016/j.patrec.2021.03.007.
Zhang, L., Chen, Y., & Li, M. (2020). Emotion recognition from facial expressions using hybrid deep learning model. IEEE Access, 8, 152659–152669. https://doi.org/10.1109/ACCESS.2020.3017325.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Yusuf Iskandar Royan, Pramono Pramono , Anindhiasti Ayu Kusuma Asri
This work is licensed under a Creative Commons Attribution 4.0 International License.
