Analisis Deteksi Keaslian Wajah Menggunakan Teknologi Eye Tracking dengan Algoritma NEEDLE
Keywords:
deteksi keaslian, eye tracking, openCV, MediaPipe, Algoritma, NEEDLEAbstract
Penelitian ini mengevaluasi deteksi keaslian wajah berbasis eye tracking dengan membandingkan dua pustaka computer vision: OpenCV dan MediaPipe. Algoritma evaluasi baru, NEEDLE (Natural Eye-movement Evaluation for Detecting Live Entities), diperkenalkan untuk menilai tiga metrik kinerja utama: Eye Detection Accuracy (EDA), Processing Speed (FPS/MS), dan Detection Stability Index (DSI). Pengujian pada kondisi terang, redup, dan penggunaan kacamata menunjukkan bahwa MediaPipe mencapai rata-rata EDA sebesar 100%, kecepatan pemrosesan 13,2 ms/frame, dan DSI sebesar 1,85, melampaui OpenCV yang hanya mencapai EDA 96,4%, kecepatan pemrosesan 29,6 ms/frame, dan DSI 0,17. Temuan ini menunjukkan bahwa MediaPipe memberikan akurasi dan stabilitas yang lebih unggul, sementara OpenCV lebih cocok untuk perangkat ringan dengan keterbatasan sumber daya. Secara keseluruhan, algoritma NEEDLE terbukti efektif sebagai kerangka evaluasi standar untuk sistem deteksi liveness biometrik.
References
[1] R. Raghavendra and C. Busch, “Presentation attack detection methods for face recognition systems: A comprehensive survey,” ACM Computing Surveys, vol. 50, no. 1, 2017. doi: 10.1145/3038924.
[2] P. P. P. Linn and E. C. Htoon, “Face Anti-spoofing using Eyes Movement and CNN-based Liveness Detection,” in Proc. ICAIT, 2019.
[3] Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face antispoofing using speeded-up robust features and Fisher vector encoding,” IEEE Signal Processing Letters, vol. 24, no. 2, pp. 141–145, 2016.
[4] A. K. Jaiswal and C. V. Lakshmi, "A Robust Face Liveness Detection System Using Eye Blink," in Proc. International Conference on Signal Processing and Communication (ICSPC), 2021.
[5] A. Hadid, "Face Biometrics under Spoofing Attacks: Vulnerabilities, Countermeasures, and Open Issues," IEEE Consumer Electronics Magazine, vol. 8, no. 4, pp. 75-81, 2019.
[6] V. Kazemi and J. Sullivan, "One Millisecond Face Alignment with an Ensemble of Regression Trees," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
[7] S. S. R. G. A. V. S. and A. N., "A Comprehensive Review on Face Liveness Detection," Journal of Physics: Conference Series, vol. 1964, no. 4, 2021.
[8] O. Jie, L. T. Ming, and T. Chi Wee, “Biometric Authentication based on Liveness Detection Using Face Landmarks and Deep Learning Model,” JOIV: International Journal on Informatics Visualization, vol. 7, no. 3‐2, pp. 1057–1065, 2023. doi: 10.30630/joiv.7.3-2.2330.
[9] S. Khairnar, S. Gite, K. Kotecha, and S. D. Thepade, “Face Liveness Detection Using Artificial Intelligence Techniques: A Systematic Literature Review and Future Directions,” Big Data and Cognitive Computing, vol. 7, no. 1, p. 37, 2023. doi: 10.3390/bdcc7010037.
[10] A. K. Geo, M. Athil, S. Hari, S. Thomas S, and K. Selvi Priya, “REAL-TIME FACIAL LIVENESS DETECTION USING MOTION VERIFICATION AND LIGHTWEIGHT CNN FOR WEB-BASED IDENTITY VERIFICATION,” International Research Journal of Modernization in Engineering Technology and Science, vol. 07, no. 04, April 2025. doi: 10.56726/IRJMETS74617.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Dani Asmara, Arya Adhyaksa Waskita, Achmad Hindasyah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
