Implementation of Identity Loss Function on Face Recognition of Low-Resolution Faces With Light CNN Architecture
Abstract
Face recognition in low-resolution images has seen significant advancements over the past few decades. Although extensive research has been conducted to improve accuracy in these conditions, one of the main challenges remains the difficulty in identifying unique facial features in low-resolution images, leading to high error rates in identification. The use of Deep Convolutional Neural Networks (DCNN) for low-resolution face recognition is still limited. However, employing super-resolution models like REAL-ESRGAN can enhance recognition accuracy in low-resolution images. This study utilizes the Light CNN architecture and applies the margin-based identity loss function AdaFace on low-resolution datasets. The model is trained using the Casia-WebFace dataset and evaluated using the LFW and TinyFace test datasets. Based on the evaluation results on the LFW test data, the best model is Light CNN9-AdaFace, achieving the highest accuracy of 97.78% at 128x128 resolution. For images with the lowest resolution of 16x16, an accuracy of 83.37% was achieved using super-resolution techniques. On the TinyFace test data, the use of super-resolution resulted in performance metrics with a Rank-1 accuracy of 47.26%, Rank-5 accuracy of 55.25%, Rank-10 accuracy of 58.61%, and Rank-20 accuracy of 61.90% using the Light CNN9-AdaFace architecture.
Downloads
References
S. Yulina, “Penerapan Haar Cascade Classifierdalam Mendeteksi Wajah dan Transformasi Citra GrayscaleMenggunakan OpenCV,” 2021. [Online]. Available: https://jurnal.pcr.ac.id/index.php/jkt/
C. Fani, “Perbandingan Identifikasi Wajah Dengan Ekstraksi Fitur Haralick Dan CNN,” 2020. [Online]. Available: http://index.unper.ac.id
H. M. Claus, “The Importance of Hyperparameter Optimisation for Facial Recognition Applications,” 2022. [Online]. Available: www.aaai.org
H. Sabilal Rasyad, F. Sthevanie, and A. Arifanto, “Pengenalan Wajah Menggunakan Metode Local Binary Pattern Dan Principal Component Analysis,” 2021.
X. Wu, R. He, Z. Sun, and T. Tan, “A Light CNN for Deep Face Representation with Noisy Labels,” Nov. 2018, [Online]. Available: http://arxiv.org/abs/1511.02683
W. Astuti, “Implementasi Metode Super Resolusi Untuk Meningkatkan Kualitas Citra Hasil Screenshot,” JURIKOM (Jurnal Riset Komputer), vol. 7, no. 3, p. 432, Jun. 2020, doi: 10.30865/jurikom.v7i3.2129.
K. S. Zebua, I. Herwidiana Kartowisastro, and G. P. Kusuma, “Low Resolution Face Recognition Using Combination Of Gpen Super Resolution And Facenet,” J Theor Appl Inf Technol, vol. 30, no. 12, 2023, [Online]. Available: www.jatit.org
J. Deng, J. Guo, J. Yang, N. Xue, I. Kotsia, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” Jan. 2018, doi: 10.1109/TPAMI.2021.3087709.
M. Kim, A. K. Jain, and X. Liu, “AdaFace: Quality Adaptive Margin for Face Recognition,” Apr. 2022, [Online]. Available: http://arxiv.org/abs/2204.00964
X. Wang, L. Xie, C. Dong, and Y. Shan, “Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data,” 2021. [Online]. Available: https://github.com/xinntao/Real-ESRGAN
D. Yi, Z. Lei, S. Liao, and S. Z. Li, “Learning Face Representation from Scratch,” Nov. 2014, [Online]. Available: http://arxiv.org/abs/1411.7923
G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments.” [Online]. Available: http://vis-www.cs.umass.edu/lfw/.
Z. Cheng, X. Zhu, and S. Gong, “Low-Resolution Face Recognition,” Nov. 2018, [Online]. Available: http://arxiv.org/abs/1811.08965
D. E. Kurniawan, K. Adi, and A. F. Rohim, “Sistem Identifikasi Biometrika Wajah Menggunakan Metode Gabor KPCA dan Mahalanobis Distance,” JSINBIS J. Sist. Inf. Bisnis, vol. 2, no. 1, pp. 006–010, Jan. 2014, doi: 10.21456/vol2iss1pp006-010
“InsightFace: an open source 2D&3D deep face analysis library.” Accessed: Jun. 14, 2023. [Online]. Available: https://insightface.ai/
Copyright (c) 2024 Tsaqif Mu'tashim Mufid, Riza Ibnu Adam, Jajam Khaeru Jaman, Garno Garno, Iqbal Maulana
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
