Cargando…
Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation
Precise iris segmentation is a very important part of accurate iris recognition. Traditional iris segmentation methods require complex prior knowledge and pre- and post-processing and have limited accuracy under non-ideal conditions. Deep learning approaches outperform traditional methods. However,...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9497583/ https://www.ncbi.nlm.nih.gov/pubmed/36141162 http://dx.doi.org/10.3390/e24091276 |
_version_ | 1784794541553876992 |
---|---|
author | Zhou, Zhiyong Liu, Yuanning Zhu, Xiaodong Liu, Shuai Zhang, Shaoqiang Li, Yuanfeng |
author_facet | Zhou, Zhiyong Liu, Yuanning Zhu, Xiaodong Liu, Shuai Zhang, Shaoqiang Li, Yuanfeng |
author_sort | Zhou, Zhiyong |
collection | PubMed |
description | Precise iris segmentation is a very important part of accurate iris recognition. Traditional iris segmentation methods require complex prior knowledge and pre- and post-processing and have limited accuracy under non-ideal conditions. Deep learning approaches outperform traditional methods. However, the limitation of a small number of labeled datasets degrades their performance drastically because of the difficulty in collecting and labeling irises. Furthermore, previous approaches ignore the large distribution gap within the non-ideal iris dataset due to illumination, motion blur, squinting eyes, etc. To address these issues, we propose a three-stage training strategy. Firstly, supervised contrastive pretraining is proposed to increase intra-class compactness and inter-class separability to obtain a good pixel classifier under a limited amount of data. Secondly, the entire network is fine-tuned using cross-entropy loss. Thirdly, an intra-dataset adversarial adaptation is proposed, which reduces the intra-dataset gap in the non-ideal situation by aligning the distribution of the hard and easy samples at the pixel class level. Our experiments show that our method improved the segmentation performance and achieved the following encouraging results: 0.44%, 1.03%, 0.66%, 0.41%, and 0.37% in the Nice1 and 96.66%, 98.72%, 93.21%, 94.28%, and 97.41% in the F1 for UBIRIS.V2, IITD, MICHE-I, CASIA-D, and CASIA-T. |
format | Online Article Text |
id | pubmed-9497583 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-94975832022-09-23 Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation Zhou, Zhiyong Liu, Yuanning Zhu, Xiaodong Liu, Shuai Zhang, Shaoqiang Li, Yuanfeng Entropy (Basel) Article Precise iris segmentation is a very important part of accurate iris recognition. Traditional iris segmentation methods require complex prior knowledge and pre- and post-processing and have limited accuracy under non-ideal conditions. Deep learning approaches outperform traditional methods. However, the limitation of a small number of labeled datasets degrades their performance drastically because of the difficulty in collecting and labeling irises. Furthermore, previous approaches ignore the large distribution gap within the non-ideal iris dataset due to illumination, motion blur, squinting eyes, etc. To address these issues, we propose a three-stage training strategy. Firstly, supervised contrastive pretraining is proposed to increase intra-class compactness and inter-class separability to obtain a good pixel classifier under a limited amount of data. Secondly, the entire network is fine-tuned using cross-entropy loss. Thirdly, an intra-dataset adversarial adaptation is proposed, which reduces the intra-dataset gap in the non-ideal situation by aligning the distribution of the hard and easy samples at the pixel class level. Our experiments show that our method improved the segmentation performance and achieved the following encouraging results: 0.44%, 1.03%, 0.66%, 0.41%, and 0.37% in the Nice1 and 96.66%, 98.72%, 93.21%, 94.28%, and 97.41% in the F1 for UBIRIS.V2, IITD, MICHE-I, CASIA-D, and CASIA-T. MDPI 2022-09-10 /pmc/articles/PMC9497583/ /pubmed/36141162 http://dx.doi.org/10.3390/e24091276 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Zhou, Zhiyong Liu, Yuanning Zhu, Xiaodong Liu, Shuai Zhang, Shaoqiang Li, Yuanfeng Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation |
title | Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation |
title_full | Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation |
title_fullStr | Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation |
title_full_unstemmed | Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation |
title_short | Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation |
title_sort | supervised contrastive learning and intra-dataset adversarial adaptation for iris segmentation |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9497583/ https://www.ncbi.nlm.nih.gov/pubmed/36141162 http://dx.doi.org/10.3390/e24091276 |
work_keys_str_mv | AT zhouzhiyong supervisedcontrastivelearningandintradatasetadversarialadaptationforirissegmentation AT liuyuanning supervisedcontrastivelearningandintradatasetadversarialadaptationforirissegmentation AT zhuxiaodong supervisedcontrastivelearningandintradatasetadversarialadaptationforirissegmentation AT liushuai supervisedcontrastivelearningandintradatasetadversarialadaptationforirissegmentation AT zhangshaoqiang supervisedcontrastivelearningandintradatasetadversarialadaptationforirissegmentation AT liyuanfeng supervisedcontrastivelearningandintradatasetadversarialadaptationforirissegmentation |