ScholarMate
English简体中文繁體中文
Customer service: 400-1616-289
Sign inSign up
Journal article

DADCNet: Dual attention densely connected network for more accurate real iris region segmentation

Chen, Ying*; Gan, Huimin; Zeng, Zhuang; Chen, Huiling南昌航空大学; y
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS2022-1DOI: 10.1002/int.22649
16Cited by7Reads
CiteSave
Share

Abstract

Most existing performance evaluation standards for iris segmentation algorithms, such as the typical recall, precision, and F-measure (RPF-measure) protocol, are based on a pixel-to-pixel comparison between the mask image obtained after segmentation and the corresponding ground truth (GT) image. However, one of the most important problems is that if the published GT images have errors when locating the iris region, then the reference value of these evaluation indicators will be reduced, which is not conducive to the development of iris recognition technology. To address this problem, this paper proposes to use a mask image segmented by a deep learning method to replace the corresponding GT image. The main work of this paper is as follows. First, a dual attention densely connected network (DADCNet) containing two attention modules and an improved skip connection is proposed to segment the real iris region more accurately than the corresponding GT image. Second, the recognition performance of the two input classes obtained from the mask image after DADCNet segmentation and the corresponding published GT image in the same recognition network is utilized to further show that the former is more reliable in positioning the real iris than the latter. To make the proposed network more convincing, extensive experiments are conducted on four representative and challenging iris databases, which is obtained under different spectral conditions. These results show that the proposed DADCNet achieves state-of-the-art performance and that the mask image obtained after DADCNet segmentation can replace the published corresponding GT image.

Disciplines and keywords

Keywords
DADCNetdual attentionground truthiris segmentation
Related
Loading…
  • Accurate iris segmentation and recognition using an end-to-end unified framework based on MADNet and DSANet
    Chen, Ying; Gan, Huimin*; Chen, Huiling*; Zeng, Yugang; Xu, Liang; Heidari, Ali Asghar; Zhu, Xiaodong; Liu, YuanningNEUROCOMPUTING, 2023, 517: 264-278.Cited by 61
  • NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization
    Wang, Caiyong; Wang, Yunlong; Zhang, Kunbo; Muhammad, Jawad; Lu, Tianhao; Zhang, Qi; Tian, Qichuan; He, Zhaofeng; Sun, Zhenan; Zhang, Yiwen; Liu, Tianbao; Yang, Wei; Wu, Dongliang; Liu, Yingfeng; Zhou, Ruiye; Wu, Huihai; Zhang, Hao; Wang, Junbao; Wang, Jiayi; Xiong, Wantong; Shi, Xueyu; Zeng, Shao; Li, Peihua; Sun, Haodong; Wang, Jing; Zhang, Jiale; Wang, Qi; Wu, Huijie; Zhang, Xinhui; Li, Haiqing; Chen, Yu; Chen, Liang; Zhang, Menghan; Sun, Ye; Zhou, Zhiyong; Boutros, Fadi; Damer, NaserInternational Joint Conference on Biometrics (IJCB), ELECTR NETWORK, 2021-08-04 To 2021-08-07.Cited by 51
  • From coarse to fine: Two-stage deep residual attention generative adversarial network for repair of iris textures obscured by eyelids and eyelashes
    Chen, Ying; Zeng, Yugang*; Xu, Liang; Guo, Shubin; Heidari, Ali Asghar; Chen, Huiling*; Zhang, Yudong*iScience, 2023, 26(7): 107169.
View all →

Publication info

Publication status
Published
Journal
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
Publication date
2022-01
Volume / issue
Vol. 37, Issue 1
Pages
829-858
DOI
10.1002/int.22649
Language
ENGLISH
Journal ranking
Q2
Output indexing
SCIE
Funding acknowledgment
National Natural Science Foundation of China [61762067, 61867004]; Natural Science Foundation of Jiangxi Province [20202BABC202029, 20202BABC202028]

Authors

  • C

    Chen, Ying (Corresponding) (First author)

    nanchang hangkong univ

  • G

    Gan, Huimin

    nanchang hangkong univ

View all 4 authorsShow fewer authors
  • Z

    Zeng, Zhuang

    nanchang hangkong univ

  • C

    Chen, Huiling

    wenzhou univ

Sign in for more features

  • Save this paper in My collections
  • Claim your outputs and generate promotion materials
  • Follow authors for new outputs
  • Join groups and collaborate
Sign up / Sign in

Products

  • ScholarMate
  • InnoCity
  • IRISaaS

Support

  • Help Center
  • Privacy Policy
  • Terms of Service

Contact

Online support: []
Customer service: 400-1616-289
Email: support@scholarmate.com

Follow or download ScholarMate

WeChat QR code
WeChat official account
App download QR code
Download the app
OutputsResearchersResearch institutionsResearch newsIRISaaS

©2026 深圳市科研之友网络服务有限公司

Public security registration badge粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417