Face Recognition Based on ResNet Architecture

Peilu Zhu

2024

Abstract

With deep learning developing, face recognition techniques are widely applied in various scenarios. Currently, most methods for achieving face recognition are based on Convolutional Neural Networks (CNN), although they have flaws. To solve the problem of long training time and improve accuracy, the Residual Network (ResNet), as a strong tool, was introduced as the main architecture in place of CNN to deal with complex data. Besides, Adam with Weight Decay (AdamW) was chosen as the optimizer and early stopping was implemented to improve model performance. 400 facial images from 40 different individuals were selected from the Olivetti faces dataset in the experiment. The experiment was conducted successfully. Losses, training time and accuracy of ResNet-18 and ResNet-50 in both 10 epochs and 30 epochs were calculated and then compared. The experimental results show that ResNet-18 performed better than ResNet-50 on such a 400 images dataset with overall lower losses and less training time. The training time is saved by 10%1̃5% after introducing the early stopping method.

Paper Citation

in Harvard Style

Zhu P. (2024). Face Recognition Based on ResNet Architecture. In Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-754-2, SciTePress, pages 18-22. DOI: 10.5220/0013486600004619

in Bibtex Style

@conference{daml24,
author={Peilu Zhu},
title={Face Recognition Based on ResNet Architecture},
booktitle={Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2024},
pages={18-22},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013486600004619},
isbn={978-989-758-754-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Face Recognition Based on ResNet Architecture
SN - 978-989-758-754-2
AU - Zhu P.
PY - 2024
SP - 18
EP - 22
DO - 10.5220/0013486600004619
PB - SciTePress