Penggunaan Deep Convolutional Neural Network (CNN) Model FaceNet untuk Fungsi Face Recognition pada Reverse Image Search
Keywords:
Deep Convolutional Neural Network, FaceNet, Reverse Image Search, Triplet Loss, Pengenalan WajahAbstract
Kemajuan teknologi digital dan meningkatnya penggunaan internet telah menimbulkan kebutuhan akan sistem yang mampu melindungi privasi pengguna, khususnya terkait penyebaran foto pribadi di dunia maya. Penelitian ini bertujuan untuk mengimplementasikan metode Deep Convolutional Neural Network (CNN) model FaceNet sebagai sistem pengenalan wajah dalam Reverse Image Search engine. Metode FaceNet digunakan untuk mengekstraksi fitur wajah dan menghasilkan representasi vektor (embedding) yang dapat dibandingkan untuk mengenali kemiripan antar wajah. Proses penelitian mencakup studi pustaka, pengumpulan data, pelatihan model FaceNet, serta evaluasi performa sistem dalam mengenali dan mencocokkan wajah. Model FaceNet memanfaatkan arsitektur Zeiler & Fergus serta Inception Network dengan fungsi kerugian Triplet Loss, yang memastikan embedding dari wajah yang sama memiliki jarak yang lebih dekat dibandingkan dengan wajah dari identitas berbeda. Hasil implementasi menunjukkan bahwa integrasi FaceNet dalam Reverse Image Search mampu meningkatkan akurasi pencarian gambar berdasarkan wajah dan mempermudah identifikasi gambar serupa secara efisien. Penelitian ini diharapkan dapat menjadi dasar bagi pengembangan sistem pelacakan identitas visual dan deteksi penggunaan gambar di berbagai platform daring.
References
Y. LeCun, Y. Bengio, dan G. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, hal. 436–444, 2015.
A. Krizhevsky, I. Sutskever, dan G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in Neural
Information Processing Systems, vol. 25, hal. 1097–1105, 2012.
F. Schroff, D. Kalenichenko, dan J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” in Proc. IEEE Conf.
Computer Vision and Pattern Recognition (CVPR), 2015, hal. 815–823.
M. D. Zeiler dan R. Fergus, “Visualizing and Understanding Convolutional Networks,” in Proc. European Conf. Computer Vision (ECCV),
, hal. 818–833.
G. B. Huang, M. Ramesh, T. Berg, dan E. Learned-Miller, “Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments,” University of Massachusetts, Amherst, 2007.
D. Yi, Z. Lei, S. Liao, dan S. Z. Li, “Learning Face Representation from Scratch,” arXiv preprint arXiv:1411.7923, 2014.
K. Zhang, Z. Zhang, Z. Li, dan Y. Qiao, “Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks,” IEEE Signal Processing Letters, vol. 23, no. 10, hal. 1499–1503, 2016.
S. Chopra, R. Hadsell, dan Y. LeCun, “Learning a Similarity Metric Discriminatively, with Application to Face Verification,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2005.
C. Szegedy, W. Liu, Y. Jia, et al., “Going Deeper with Convolutions,” Proc. IEEE Conf. Computer Vision and Pattern Recognition
(CVPR), 2015.
A. Vaswani, N. Shazeer, N. Parmar, et al., “Attention Is All You Need,” Advances in Neural Information Processing Systems, vol. 30, 2017.
T. Ahonen, A. Hadid, dan M. Pietikäinen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, hal. 2037–2041, 2006.
X. Wu, R. He, Z. Sun, dan T. Tan, “A Light CNN for Deep Face Representation with Noisy Labels,” IEEE Transactions on Information
Forensics and Security, vol. 13, no. 11, hal. 2884–2896, 2018.
J. Deng, J. Guo, N. Xue, dan S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2019.
S. Ge, J. Zhao, C. Li, dan J. Li, “Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation,” IEEE Transactions on Image Processing, vol. 28, no. 4, hal. 2051–2062, 2019.
J. Philbin, O. Chum, M. Isard, J. Sivic, dan A. Zisserman, “Object Retrieval with Large Vocabularies and Fast Spatial Matching,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2007.
