Bayesian-optimized Support Vector Machine for Indonesian Ethnicity Classification Based on FaceNet Facial Features

Alfito Juanda; Umar Zaky

doi:10.58526/jsret.v5i1.983

Authors

Alfito Juanda Department of Informatics, Faculty of Sains and Technology, Universitas Teknologi Yogyakarta
Umar Zaky Information Systems, Universitas Teknologi Yogyakarta

DOI:

https://doi.org/10.58526/jsret.v5i1.983

Keywords:

Ethnicity Classification, Facial Image, Deep Learning, FaceNet, Support Vector Machine, Bayesian Optimization

Abstract

The classification of ethnic groups in Indonesia based on facial images faces significant challenges due to high morphological diversity and the limitations of existing computational methods in handling local ethnic variations. This research developed a hybrid classification system to address this problem. The system was built through several stages: collecting a primary dataset of 550 facial images from five ethnic groups (Acehnese, Batak, Florenese, Javanese, and Papuan), extracting facial features using the FaceNet (InceptionResnetV1) model to generate face embeddings, and classification using a Support Vector Machine (SVM). To achieve maximum precision, the SVM model's hyperparameters were automatically tuned using Bayesian Optimization. The model's capabilities were confirmed using an 80/20 training-testing split, resulting an impressive 94.55% of accuracy. Its high discriminative power was further solidified by a stellar 0.9930 AUC-ROC score. Closer inspection showed a fascinating dichotomy: the model pinpointed the Papuan ethnicity with perfect precision, though it occasionally faltered when faced with the subtle morphological overlaps found in other ethnic groups. This study demonstrates that the combination of deep learning feature extraction with an optimized SVM classifier is an effective and robust approach for complex ethnicity classification, successfully providing an accurate and objective classification solution.

Downloads

Download data is not yet available.

References

Baydhowi, B., Purwono, U., Prathama Siswadi, A. G., Ali, M. M., Syahputra, W., & Iskandar, T. Z. (2023). Perception of threat and national identity: Investigation of the mediating role of collective self esteem. Heliyon, 9(6). https://doi.org/10.1016/j.heliyon.2023.e17207

Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018). VGGFace2: A dataset for recognising faces across pose and age. http://arxiv.org/abs/1710.08092

Chun, C., & Wang, W. Y. (n.d.). Face Recognition with Sub-Sampled Images.

Das, S. R., Champatyray, S., & Panda, D. K. (2025). Anthropometric analysis of facial dimensions using 3D imaging for forensic identification and ethnicity-specific reference models. Forensic Science International: Reports, 12. https://doi.org/10.1016/j.fsir.2025.100428

Delta Pantika putri. (n.d.). DETEKSI SUKU/RAS DI INDONESIA BERDASARKAN WAJAH MENGGUNAKAN METODE INSTANCESEGEMENTATION MASK-RCNN.

Elshewey, A. M., Shams, M. Y., El-Rashidy, N., Elhady, A. M., Shohieb, S. M., & Tarek, Z. (2023). Bayesian Optimization with Support Vector Machine Model for Parkinson Disease Classification. Sensors, 23(4). https://doi.org/10.3390/s23042085

Fajri, M., & Primajaya, A. (2023). Komparasi Teknik Hyperparameter Optimization pada SVM untuk Permasalahan Klasifikasi dengan Menggunakan Grid Search dan Random Search. In Journal of Applied Informatics and Computing (JAIC) (Vol. 7, Issue 1). http://jurnal.polibatam.ac.id/index.php/JAIC

Greif, L., Hübschle, N., Kimmig, A., Kreuzwieser, S., Martenne, A., & Ovtcharova, J. (2025). Structured sampling strategies in Bayesian optimization: evaluation in mathematical and real-world scenarios. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-025-02597-2

Hakim, S. U. El, Arifianto, R., Sugiyanto, S., Pratiwi, I. A. P., Bahari, G., & Krisnaputra, R. (2025). Bamboo Diameter Detection System Based on Image Processing as a Pre-Assessment for an Automated Bamboo Splitting Technology. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control. https://doi.org/10.22219/kinetik.v10i2.2170

Hancock, P. B., & Burton, A. M. (1996). Face processing: Human perception and principal components analysis. In Memory & Cognition (Vol. 24, Issue I).

Kalkatawi, A.-A., & Saeed, U. (2024). Ethnicity Classification Based on Facial Images using Deep Learning Approach. In IJACSA) International Journal of Advanced Computer Science and Applications (Vol. 15, Issue 2). www.ijacsa.thesai.org

Kokare, S., & Ghisare, V. (n.d.). SVM-Based Approach for Human Face Detection and Recognition. In International Journal on Science and Technology.

Kotwal, K., & Marcel, S. (2025). Review of Demographic Fairness in Face Recognition. https://doi.org/10.1109/TBIOM.2025.3601217

Li, H. C., Deng, Z. Y., & Chiang, H. H. (2020). Lightweight and resource-constrained learning network for face recognition with performance optimization. Sensors (Switzerland), 20(21), 1–20. https://doi.org/10.3390/s20216114

Malu, M., Dasarathy, G., & Spanias, A. (n.d.). Bayesian Optimization in High-Dimensional Spaces: A Brief Survey. https://distill.pub/2020/bayesian-optimization/.

Melzi, P., Rathgeb, C., Tolosana, R., Vera-Rodriguez, R., Morales, A., Lawatsch, D., Domin, F., & Schaubert, M. (2024). Synthetic Data for the Mitigation of Demographic Biases in Face Recognition. http://arxiv.org/abs/2402.01472

Montesinos López, O. A., Montesinos López, A., & Crossa, J. (2022). Support Vector Machines and Support Vector Regression. In Multivariate Statistical Machine Learning Methods for Genomic Prediction (pp. 337–378). Springer International Publishing. https://doi.org/10.1007/978-3-030-89010-0_9

Ningsih, M. R., Unjung, J., Pertiwi, D. A. A., Prasetiyo, B., & Muslim, M. A. (2024). Optimized Support Vector Machine with Particle Swarm Optimization to Improve the Accuracy Amazon Sentiment Analysis Classification. KINETIK, 9(1), 101–108. https://kinetik.umm.ac.id/index.php/kinetik/article/view/1888https://kinetik.umm.ac.id/index.php/kinetik/article/view/1888

Nuraeni, N., & Faisal, M. (2025). Classification of Sleep Disorders Using Support Vector Machine. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control. https://doi.org/10.22219/kinetik.v10i1.2054

PARDEDE, J., & KLEB, S. S. (2024). Face Race Classification using ResNet-152 and DenseNet- 121. ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, 12(3), 798. https://doi.org/10.26760/elkomika.v12i3.798

Patel, S., & Ranjan Kisku, D. (n.d.). Improving Bias in Facial Attribute Classification: A Combined Impact of KL Divergence induced Loss Function and Dual Attention.

PilarGautama, H., Prasetiyowati, S. S., & Sibaroni, Y. (2025). Land Price Distribution Prediction in Jakarta Using Support Vector Machine with Feature Expansion and Kriging Interpolation. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control. https://doi.org/10.22219/kinetik.v10i3.2216

Putri, T. T., Rachmawati, E., & Sthevanie, F. (2020, November 10). Indonesian Ethnicity Recognition Based on Face Image Using Uniform Local Binary Pattern (ULBP) and Color Histogram. ICICoS 2020 - Proceeding: 4th International Conference on Informatics and Computational Sciences. https://doi.org/10.1109/ICICoS51170.2020.9299103

Putriany, D. M., Rachmawati, E., & Sthevanie, F. (2021). Indonesian Ethnicity Recognition Based on Face Image Using Gray Level Co-occurrence Matrix and Color Histogram. IOP Conference Series: Materials Science and Engineering, 1077(1), 012040. https://doi.org/10.1088/1757-899x/1077/1/012040

Rizkallah, L. W. (2025). Optimizing SVM hyperparameters for satellite imagery classification using metaheuristic and statistical techniques. International Journal of Data Science and Analytics, 20(5), 4945–4962. https://doi.org/10.1007/s41060-025-00762-7

Saradhi, T. V. (2025). A Study on Hyperparameter Tuning in Support Vector Machines and its Impact on Model Accuracy. In Global Journal of Engineering Innovations & Interdisciplinary Research GJEIIR (Vol. 5, Issue 1).

Schroff, F., & Philbin, J. (n.d.). FaceNet: A Unified Embedding for Face Recognition and Clustering.

Septyono, M. B., Anggraeny, F. T., & Mumpuni, R. (n.d.). JIP (Jurnal Informatika Polinema) Pengenalan Ekspresi Wajah dengan LBP dan Multi-Level CNN.

Wang, K., Wang, S., Zhang, P., Zhou, Z., Zhu, Z., Wang, X., Peng, X., Sun, B., Li, H., & You, Y. (n.d.). An Efficient Training Approach for Very Large Scale Face Recognition.

Wirayuda, T. A. B., Munir, R., & Kistijantoro, A. I. (2023). Compact-Fusion Feature Framework for Ethnicity Classification. Informatics, 10(2). https://doi.org/10.3390/informatics10020051

Wirianto, & Mauritsius, T. (2021). The development of face recognition model in indonesia pandemic context based on dcnn and arcface loss function. International Journal of Innovative Computing, Information and Control, 17(5), 1513–1530. https://doi.org/10.24507/ijicic.17.05.1513

Yucer, S., Tektas, F., Al Moubayed, N., & Breckon, T. P. (n.d.). Measuring Hidden Bias within Face Recognition via Racial Phenotypes.