Analisis Konseptual Fusi Multimodal Wajah dan Visual Speech untuk Autentikasi Biometrik Non-Vokal terhadap Deepfake
DOI:
https://doi.org/10.71302/jbidai.v8i2.84Kata Kunci:
biometrik multimodal, pengenalan wajah, fusi level skor, deepfake, liveness detectionAbstrak
Sistem autentikasi biometrik masih menghadapi keterbatasan mendasar, khususnya pada pendekatan unimodal yang rentan terhadap variasi lingkungan dan serangan pemalsuan visual. Untuk mengatasi permasalahan tersebut, biometrik multimodal yang mengintegrasikan ciri fisiologis dan perilaku menjadi pendekatan yang semakin relevan. Penelitian ini menyajikan kajian analitis terhadap riset-riset terkini di bidang biometrik multimodal visual dengan fokus pada strategi fusi level skor serta integrasi pengenalan wajah statis dan gerakan bibir dinamis sebagai mekanisme autentikasi non-vokal. Hasil sintesis literatur menunjukkan bahwa fusi level skor merupakan pendekatan yang paling fleksibel dan stabil dalam menggabungkan modalitas biometrik yang heterogen, terutama pada kombinasi ciri spasial statis dan pola temporal dinamis. Selain itu, arsitektur deep learning berbasis Transformer diidentifikasi memiliki potensi signifikan dalam memodelkan dependensi temporal pada gerakan bibir. Kajian ini juga menyoroti tantangan keamanan utama, khususnya serangan presentasi dan visual-only deepfake, serta menekankan pentingnya deteksi keaslian berbasis dinamika visual sebagai bagian integral dari sistem autentikasi. Berdasarkan analisis tersebut, penelitian ini merumuskan kerangka konseptual autentikasi biometrik visual multimodal yang mengintegrasikan verifikasi identitas dan liveness detection dalam satu alur proses, sekaligus mengidentifikasi peluang riset lanjutan meliputi pemanfaatan self-supervised learning, optimasi model untuk perangkat dengan sumber daya terbatas, dan perancangan frasa sandi visual yang lebih diskriminatif.
Referensi
[1] A. Roihan et al., “Perancangan Purwarupa Sistem Keamanan Kunci Pintu Berbasis Pengenalan Wajah”, Journal of Innovation And Future Technology (IFTECH), vol. 6, no. 2, pp. 234–242, Aug. 2024, doi: 10.47080/iftech.v6i2.3415.
[2] A. Ross and A. K. Jain, “Multimodal biometrics: An overview,” Proc. 12th European Signal Processing Conference, 2004. doi: 10.1109/EUSIPCO.2004.7075379.
[3] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2015, pp. 815–823. doi: 10.1109/CVPR.2015.7298682.
[4] R. Raghavendra and C. Busch, “Presentation attack detection methods for face recognition systems: A comprehensive survey,” IEEE Access, vol. 7, pp. 100–132, 2019. doi: 10.1109/ACCESS.2019.2929433.
[5] J. S. Chung, A. Senior, O. Vinyals, and A. Zisserman, “Lip reading sentences in the wild,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 3444–3453. doi: 10.1109/CVPR.2017.367.
[6] T. Afouras, J. S. Chung, and A. Zisserman, “Deep lip reading: A comparison of models and an online application,” IEEE/ACM Trans. Audio, Speech, and Language Processing, vol. 26, no. 12, pp. 2246–2260, 2018. doi: 10.1109/TASLP.2018.2810139.
[7] J. Yang, A. Waibel, and A. Jain, “Biometric recognition: Challenges and opportunities,” IEEE Computer, vol. 44, no. 1, pp. 74–80, 2011. doi: 10.1109/MC.2010.384.
[8] P. K. Ratha, K. Ricanek, and M. Savvides, “Score level fusion of multimodal biometrics using triangular norms,” Pattern Recognition Letters, vol. 32, no. 14, pp. 1843–1850, 2011. doi:10.1016/j.patrec.2011.06.029.
[9] O. N., Kadhim, M. H., Abdulameer, Y. M. H., Al-Mayali, “A multimodal biometric system for iris and face traits based on hybrid approaches and score level fusion,” In BIO Web of Conferences, vol. 97, pp. 00016, 2024. doi: 10.1051/bioconf/20249700016.
[10] S. R. B. Kisku, J. S. Chang, and A. Kumar, “Multimodal biometrics: Weighted score level fusion based on non-ideal iris and face images,” Expert Systems with Applications, vol. 41, no. 11, pp. 5390–5404, 2014. doi:10.1016/j.eswa.2014.02.051.
[11] M. He et al., “Performance evaluation of score level fusion in multimodal biometric systems,” Pattern Recognition, vol. 43, no. 5, pp. 1789–1800, 2010. doi:10.1016/j.patcog.2009.11.018.
[12] A. Naseem et al., “Robust multimodal biometric system based on optimal score level fusion model,” Expert Systems with Applications, vol. 116, pp. 364–376, 2019. doi:10.1016/j.eswa.2018.08.036.
[13] S. Tharewal et al., “Score-Level Fusion of 3D Face and 3D Ear for Multimodal Biometric Human Recognition,” Computational Intelligence and Neuroscience, 2022, Art. no. 3019194. doi:10.1155/2022/3019194.
[14] S. N. Garg, R. Vig, and S. Gupta, “A Survey on Different Levels of Fusion in Multimodal Biometrics,” Indian Journal of Science and Technology, vol. 10, no. 44, pp. 1–11, 2017. doi:10.17485/ijst/2017/v10i44/120575.
[15] F. Wang and J. Han, “Multimodal biometric authentication based on score level fusion using support vector machine,” Opto-Electronics Review, vol. 17, no. 1, pp. 59–64, 2009. doi:10.2478/s11772-008-0054-8.
[16] F., Shafizadegan, A. R., Naghsh-Nilchi, E. Shabaninia, “Multimodal vision-based human action recognition using deep learning: a review,” Artificial Intelligence Review, vol. 57, 178, 2024. doi:10.1007/s10462-024-10730-5
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
