Implementation of Identity Loss Function on Face Recognition of Low-Resolution Faces With Light CNN Architecture

  • Tsaqif Mu'tashim Mufid Universitas Singaperbangsa Karawang
  • Riza Ibnu Adam Universitas Singaperbangsa Karawang
  • Jajam Khaeru Jaman Universitas Singaperbangsa Karawang
  • Garno Garno Universitas Singaperbangsa Karawang
  • Iqbal Maulana Universitas Singaperbangsa Karawang
Keywords: AdaFace, Face recognition, Low-resolution images, Super-resolution, 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

Download data is not yet available.

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/

Published
2024-07-07
How to Cite
[1]
T. Mufid, R. Adam, J. Jaman, G. Garno, and I. Maulana, “Implementation of Identity Loss Function on Face Recognition of Low-Resolution Faces With Light CNN Architecture”, JAIC, vol. 8, no. 1, pp. 91-97, Jul. 2024.
Section
Articles

Most read articles by the same author(s)