DETEKSI DAN KLASIFIKASI CITRA WAJAH MENGGUNAKAN MTCNN DAN MOBILENET
Keywords:
Deteksi Wajah, MTCNN, MobileNet, Pengenalan Wajah, KlasifikasiAbstract
Pengenalan wajah (face recognition) merupakan bidang penting dalam teknologi biometric modern. Penelitian ini mengembangkan sistem yang mengombinasikan Multi -task Cascaded Convolutional Networks (MTCNN) sebagai metode deteksi wajah dan MobileNet sebagai metode klasifikasi citra wajah.Kombinasi ini dipilih karena kecepatan, akurasi, dan efisiensinya dalam sistem berbasis sumber daya terbatas. Dataset yang digunakan terdiri dari 30 label wajah yang merupakan kombinasi data publik (Pins Face Recognition) dan dataset pribadi, dengan total 1800 gambar. MTCNN digunakan untuk mendeteksi wajah dalam gambar dan mengekstrak bounding box, yang kemudian diklasifikasikan menggunakan MobileNet yang telah dimodifikasi melalui transfer learning dan fine-tuning. Model dievaluasi berdasarkan metrik akurasi, precision, recall, F1-score, dan confusion matrix. Hasil evaluasi global menunjukkan akurasi validasi mencapai 93%, serta nilai F1-score makro sebesar 0.93. Penelitian ini membuktikan bahwa system pengenalan wajah berbasis deep learning dapat bekerja secara efisien pada skenario data terbatas, dengan potensi implementasi pada perangkat embedded dan aplikasi real-time. Penelitian ini memberikan kontribusi nyata dalam mendesain sistem biometrik ringan dengan akurasi tinggi.
References
Amri, H. (2025). Real-time face attendance system using cnn mobilenet and mtcnn. J. Teknologi dan Open Source, 5(1), 22–30.
Debnath, S., Ejaz, M. S., & Saha, K. (2024). Improving students' residence hall security with machine learning techniques. 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), 1-5. https://doi.org/10.1109/ICRPSET64863.2024.10955908.
Du, H., Shi, H., Zeng, D., Zhang, X. P., & Mei, T. (2022). The elements of end-to-end deep face recognition: A survey of recent advances. ACM Comput. Surv., 54(10s), Article 212, 42 halaman.https://doi.org/10.1145/3507902.
Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multi-task cascaded convolutional networks. arXiv:1604.02878v1 [cs.CV].https://doi.org/10.48550/arXiv.1604.02878
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. -C. (2019). MobileNetV2: Inverted residuals and linear bottlenecks. arXiv:1801.04381v4 [cs.CV].https://doi.org/10.48550/arXiv.1801.04381
Gupta, V., & Rajput, R. (2021). Face mask detection using mtcnn and mobilenetv2. IRJET: International Research Journal of Engineering and Technology, 8 (3), 309-312.
Cao, J., Pang, R., Ma, R., & Qi, Y. (2021). Face mask recognition based on mtcnn and mobilenet. Dalam:Li, Y., Zhu, Q., Qiao, F., Fan, Z., Chen, Y. (eds) Advances in Simulation and Process Modelling. ISSPM 2020. Advances in Intelligent Systems and Computing, 1305. Springer.https://doi.org/10.1007/978-98133-4575-1_41
Sukkar, V., & Ercelebi, E. (2023). A real-time face recognition based on mobilenetv2 model. BAJECE:Balk. J. Electr. Comput. Eng, 1(1), 31-39.
Pham, T. N., Nguyen, N. P., Dinh, N. M. Q., & Le, T. (2022). Tracking student attendance in virtual classes based on MTCNN and FaceNet. In Intelligent Information and Database Systems: 14th Asian Conference, ACIIDS 2022, 382–394. Springer-Verlag. https://doi.org/10.1007/978-3-031-21967-2_31.
Sheikh, B., & Zafar, A. (2025). Lights, Camera, Adversary: Decoding the enigmatic world of malicious frames in real-time video surveillance systems. Neural Process Lett 57, 46. https://doi.org/10.1007/s11063-025-11756-8.
Kaggle Dataset. (2020). Pins face recognition. https://www.kaggle.com/datasets/hereisburak/pins-facerecognition.
Kumar, B. A., & Bansal, M. (2023). Face mask detection on photo and real -time video images using Caffe-MobileNetV2 transfer learning. Applied Sciences, 13(2), 935.https://doi.org/10.3390/app13020935.
Li, L., & Zhang, Q. (2024). Intelligent education managemnt system design for universities based on mtcnn face recognition algorithm. Scalable Computing: Practice and Experience, 25(4), 2463-2475.
Lu, Z., Zhou, C., & Wang, H. (2024). A face detection and recognition method built on the improved MobileFaceNet. International Journal of Sensor Networks, 45(3), 166-176.
Zhang, J. (2025). Student apartment access control system based on mtcnn-facenet algorithm. International Journal of Computational Intelligence and Applications, 24(1), 2450022. https://doi.org/10.1142/S1469026824500226.
Shukla, R. K., & Tiwari, A. K. (2023). Masked Face Recognition Using MobileNet V2 with Transfer Learning. Computer Systems Science and Engineering, 45(1), 293–309.https://doi.org/10.32604/csse.2023.027986
Durai, S., Sujithra, T., Satyam, B. V., Keshetty, S. N., Sagar, C. N. S., & Charan, A. S. (2024). Real time facial recognition-based criminal identification using mtcnn. 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS), 1261-1265.https://doi.org/10.1109/ICSCSS60660.2024.10624946.
Rahman, Md. H., Jannat, M. K. A., Islam, Md. S., Grossi, G., Bursic, S., & Aktaruzzaman, Md. (2023).Real-time face mask position recognition system based on MobileNet model. Smart Health, 28. https://doi.org/10.1016/j.smhl.2023.100382.
Kocacinar, B., Tas, B., Akbulut, F. P., Catal, C., & Mishra, D. (2022). A Real -Time CNN-Based Lightweight Mobile Masked Face Recognition System. IEEE Access, 10, 63496-63507. https://doi.org/10.1109/ACCESS.2022.3182055.
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). ArcFace: Additive Angular Margin Loss for Deep Face Recognition. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4685-4694, https://doi.org/10.1109/CVPR.2019.00482.
Guo, Y., & Wünsche, B. C. (2020). Comparison of Face Detection Algorithms on Mobile Devices. 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), 1-6.https://doi.org/10.1109/IVCNZ51579.2020.9290542.
