Comparative Analysis of Different Deep Learning Models on Face Recognition Tasks

Xinhang Lin

2024

Abstract

Deep learning models have strong non-linear fitting capabilities and feature extraction capabilities, and they are increasingly widely used in the field of face recognition. Among them, the convolutional neural network (CNN), deep belief network (DBN), and generative adversarial network (GAN) three models have attracted wide attention. This paper summarizes the basic principles of the three models and their application in the field of face recognition, analyzes the advantages and disadvantages of the three models, and compares them. CNN has the strongest feature extraction ability and is the most widely used. GAN is often used in the face data enhancement field. The disadvantages of deep learning models are also obvious, they require a large amount of computational resources and training data and also have a poor ability to fit special data such as occluded data and dynamic data. The application of the deep learning model in the field of face recognition still needs further research.

Paper Citation

in Harvard Style

Lin X. (2024). Comparative Analysis of Different Deep Learning Models on Face Recognition Tasks. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 211-217. DOI: 10.5220/0012870000004547

in Bibtex Style

@conference{icdse24,
author={Xinhang Lin},
title={Comparative Analysis of Different Deep Learning Models on Face Recognition Tasks},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={211-217},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012870000004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Comparative Analysis of Different Deep Learning Models on Face Recognition Tasks
SN - 978-989-758-690-3
AU - Lin X.
PY - 2024
SP - 211
EP - 217
DO - 10.5220/0012870000004547
PB - SciTePress