Cascade attention feature residual fusion network for iris localization and segmentation in non-cooperative environments

•Proposed a cascade attention feature residual fusion network (CA-RFNet).•Deep convolutional residual blocks in the encoder to enhance feature representation capability.•Cascade attention fusion modules in skip connections for adaptive multiscale feature fusion and information complementarity.•Bound...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Displays Jg. 91; S. 103192
Hauptverfasser: Guo, Shubin, Chen, Ying, Deng, Junkang, Chen, Huiling, Chen, Zhijie, He, Changle, Zhu, Xiaodong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.01.2026
Schlagworte:
ISSN:0141-9382
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •Proposed a cascade attention feature residual fusion network (CA-RFNet).•Deep convolutional residual blocks in the encoder to enhance feature representation capability.•Cascade attention fusion modules in skip connections for adaptive multiscale feature fusion and information complementarity.•Boundary perception modules in the decoder to reinforce edge information.•Verified the localization and segmentation performance of CA-RFNet on iris datasets in non-cooperative environments. Iris localization and segmentation constitute mission-critical preprocessing stages in iris recognition systems, where their precision directly governs overall recognition accuracy. However, iris images captured under non-cooperative conditions are prone to boundary distortions caused by eyelash or eyelid occlusions and defocus blurring, while texture features suffer from weakened saliency due to uneven illumination or specular reflections, leading to reduced algorithm robustness. To address these challenges, this paper proposes a cascade attention feature residual fusion network (CA-RFNet) for multitask iris localization and segmentation in unconstrained scenarios. CA-RFNet adopts an encoder-decoder structure with skip connections. In the encoder stage, deep convolutional residual blocks hierarchically extract iris texture features. A cascade attention fusion module embedded in skip connections dynamically weights and adaptively integrates multi-receptive-field features while enabling cross-scale information complementarity. The decoder incorporates a boundary perception module with cross-layer feature interaction mechanisms to enhance fine-grained structural perception and cross-hierarchy semantic representation, thereby improving edge prediction accuracy. CA-RFNet modules work collaboratively to overcome adverse effects of unconstrained subject behaviors and complex environmental interference on algorithm robustness in non-cooperative scenarios. Extensive experiments on five non-cooperative iris datasets (CASIA-Iris-Distance, CASIA-Iris-Complex-Occlusion, CASIA-Iris-Complex-Off-angle, CASIA-Iris-M1, and CASIA-Iris-Africa) demonstrate that CA-RFNet achieves superior segmentation and localization performance on challenging samples with complex noise factors including occlusion, off-angle, illumination variation, specular reflection, dark iris, and dark skin.
AbstractList •Proposed a cascade attention feature residual fusion network (CA-RFNet).•Deep convolutional residual blocks in the encoder to enhance feature representation capability.•Cascade attention fusion modules in skip connections for adaptive multiscale feature fusion and information complementarity.•Boundary perception modules in the decoder to reinforce edge information.•Verified the localization and segmentation performance of CA-RFNet on iris datasets in non-cooperative environments. Iris localization and segmentation constitute mission-critical preprocessing stages in iris recognition systems, where their precision directly governs overall recognition accuracy. However, iris images captured under non-cooperative conditions are prone to boundary distortions caused by eyelash or eyelid occlusions and defocus blurring, while texture features suffer from weakened saliency due to uneven illumination or specular reflections, leading to reduced algorithm robustness. To address these challenges, this paper proposes a cascade attention feature residual fusion network (CA-RFNet) for multitask iris localization and segmentation in unconstrained scenarios. CA-RFNet adopts an encoder-decoder structure with skip connections. In the encoder stage, deep convolutional residual blocks hierarchically extract iris texture features. A cascade attention fusion module embedded in skip connections dynamically weights and adaptively integrates multi-receptive-field features while enabling cross-scale information complementarity. The decoder incorporates a boundary perception module with cross-layer feature interaction mechanisms to enhance fine-grained structural perception and cross-hierarchy semantic representation, thereby improving edge prediction accuracy. CA-RFNet modules work collaboratively to overcome adverse effects of unconstrained subject behaviors and complex environmental interference on algorithm robustness in non-cooperative scenarios. Extensive experiments on five non-cooperative iris datasets (CASIA-Iris-Distance, CASIA-Iris-Complex-Occlusion, CASIA-Iris-Complex-Off-angle, CASIA-Iris-M1, and CASIA-Iris-Africa) demonstrate that CA-RFNet achieves superior segmentation and localization performance on challenging samples with complex noise factors including occlusion, off-angle, illumination variation, specular reflection, dark iris, and dark skin.
ArticleNumber 103192
Author He, Changle
Deng, Junkang
Chen, Ying
Chen, Huiling
Guo, Shubin
Zhu, Xiaodong
Chen, Zhijie
Author_xml – sequence: 1
  givenname: Shubin
  surname: Guo
  fullname: Guo, Shubin
  email: gsb_0810@163.com
  organization: School of Software, Nanchang Hangkong University, Nanchang 330063, China
– sequence: 2
  givenname: Ying
  surname: Chen
  fullname: Chen, Ying
  email: c_y2008@163.com
  organization: School of Software, Nanchang Hangkong University, Nanchang 330063, China
– sequence: 3
  givenname: Junkang
  surname: Deng
  fullname: Deng, Junkang
  email: 1440945010@qq.com
  organization: School of Software, Nanchang Hangkong University, Nanchang 330063, China
– sequence: 4
  givenname: Huiling
  surname: Chen
  fullname: Chen, Huiling
  email: chenhuiling.jlu@gmail.com
  organization: Department of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
– sequence: 5
  givenname: Zhijie
  surname: Chen
  fullname: Chen, Zhijie
  email: 2822972120@qq.com
  organization: School of Software, Nanchang Hangkong University, Nanchang 330063, China
– sequence: 6
  givenname: Changle
  surname: He
  fullname: He, Changle
  email: 1163968399@qq.com
  organization: School of Software, Nanchang Hangkong University, Nanchang 330063, China
– sequence: 7
  givenname: Xiaodong
  surname: Zhu
  fullname: Zhu, Xiaodong
  email: wsteqdzh@163.com
  organization: School of Software, Nanchang Hangkong University, Nanchang 330063, China
BookMark eNp9kMtOwzAQRb0oEm3hD1j4B1Js106cDRKqeEmV2MDamtpj5JLalZ2Wx9eTEtasRrqaczVzZmQSU0RCrjhbcMbr6-3ChbLvYCGYUEO05K2YkCnjklftUotzMitlyxgTshFT8rmCYsEhhb7H2IcUqUfoDxlpxhLcATrqD-WUR-w_Un6nPmUacii0Sxa68A2_FERHC77thpIxCAORYmVT2mMeoiNSjMeQUzztlAty5qErePk35-T1_u5l9Vitnx-eVrfrygrV9JWsawVYe-2criX3stG8BdFYhrX2G6uU01JbPbznASyKjWylUs2wDK3aqOWcyLHX5lRKRm_2OewgfxnOzMmY2ZrRmDkZM6OxAbsZMRxuOwbMptiA0aILGW1vXAr_F_wAcN590A
Cites_doi 10.1007/s10489-022-03973-8
10.1109/ICCV48922.2021.00986
10.11834/jig.210078
10.3390/electronics14020246
10.1109/ICCVW60793.2023.00361
10.1007/s42044-023-00157-6
10.1007/s13042-024-02232-1
10.1016/j.neucom.2022.10.064
10.1002/int.22649
10.1007/s00530-024-01280-5
10.1109/CCDC62350.2024.10588166
10.1007/978-3-031-20233-9_41
10.1007/s11042-021-11075-9
10.1007/978-3-319-24574-4_28
10.1142/S0219467824500426
10.1016/j.bspc.2025.107595
10.1109/TIFS.2020.2980791
10.1016/j.dsp.2021.103244
10.1109/ICSCN.2017.8085713
10.1117/1.JEI.31.5.053035
10.1007/978-3-031-91989-3_12
10.1109/TIFS.2023.3268504
10.1109/TIFS.2024.3407508
10.1109/CVPR.2018.00474
10.1109/CVPR.2018.00745
10.1109/CVPR.2016.90
10.1145/3651306
10.1134/S1054661824700743
10.1016/j.asoc.2025.113009
10.1109/TCSVT.2003.818350
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright_xml – notice: 2025 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.displa.2025.103192
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_displa_2025_103192
S014193822500229X
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29G
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
9JO
AABXZ
AAEDT
AAEDW
AAEPC
AAFJI
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABFNM
ABIVO
ABJNI
ABMAC
ABMMH
ABWVN
ABXDB
ABXRA
ACDAQ
ACGFS
ACLOT
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADJOM
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AEZYN
AFJKZ
AFPUW
AFRZQ
AFTJW
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOMHK
AOUOD
APXCP
ASPBG
AVARZ
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MAGPM
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PRBVW
Q38
R2-
ROL
RPZ
SBC
SDF
SDG
SES
SET
SEW
SPC
SPCBC
SSB
SSM
SSO
SST
SSV
SSZ
T5K
TN5
WUQ
XPP
ZMT
~G-
~HD
9DU
AAYXX
CITATION
ID FETCH-LOGICAL-c257t-4665ae6f8dd8641f47819a27c0e68fbc55d848c8141faace2b494557864a95b53
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001563420500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0141-9382
IngestDate Sat Nov 29 06:55:51 EST 2025
Sat Sep 27 17:12:46 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords CA-RFNet
Boundary perception module
Iris localization and segmentation
Cascade attention fusion module
Deep convolutional residual block
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c257t-4665ae6f8dd8641f47819a27c0e68fbc55d848c8141faace2b494557864a95b53
ParticipantIDs crossref_primary_10_1016_j_displa_2025_103192
elsevier_sciencedirect_doi_10_1016_j_displa_2025_103192
PublicationCentury 2000
PublicationDate January 2026
2026-01-00
PublicationDateYYYYMMDD 2026-01-01
PublicationDate_xml – month: 01
  year: 2026
  text: January 2026
PublicationDecade 2020
PublicationTitle Displays
PublicationYear 2026
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Yin, He, Zhang (b0015) 2025
Liu, Shen, Wu (b0160) 2023; 53
Jan, Alrashed, Min-Allah (b0055) 2024; 83
J. Hu, L. Shen, G. Sun, Squeeze‐and‐excitation networks[C], in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
Z. Jia, J. Deng, L. Chi, et al., CondSeg: Ellipse estimation of pupil and iris via conditioned segmentation[J]. arXiv preprint arXiv:2408.17231, 2024.
Guo, Chen, Zeng (b0070) 2022
Sun, Lu, Liu (b0150) 2022; 31
L. Yang, R.Y. Zhang, L. Li, et al., SimAM: A simple, parameter-free attention module for convolutional neural networks[C], in: Proceedings of the 38th International Conference on Machine Learning (PMLR). 2021, 139: 11863-11874.
Samarin, Savelev, Toropov (b0185) 2024; 34
Wang, Muhammad, Wang (b0145) 2020; 15
S. Zhang, S. Zhang, Improved three-dimensional gaze estimation with precise iris segmentation based on YOLOv8[C], in: Proceedings of the 2024 36th Chinese Control and Decision Conference (CCDC), 2024, pp. 1970–1974.
Bonyani, Ghanbari, Rad (b0105) 2024; 15
Pan, Xiong (b0045) 2021; 33
Avhad, Bakal (b0125) 2025; 105
Yan, Wang, Zhu (b0170) 2024; 30
He, Yang, Zheng (b0190) 2025; 55
K. He, X. Zhang, S. Ren, et al., Deep residual learning for image recognition[C], in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
Sun, He, Wang (b0005) 2021; 26
Pourafkham, Khotanlou (b0100) 2024
Daugman (b0040) 2004; 14
Jiang, Zhang, Wang (b0130) 2025; 14
Khaki (b0080) 2024; 24
A. Hossain, T. Sultan, S. Schuckers, Post-mortem human iris segmentation analysis with deep learning[J], 2024. arXiv preprint arXiv:2408.03448.
M. Sandler, A. Howard, M. Zhu, et al., MobileNetV2: Inverted residuals and linear bottlenecks[C], in: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2018, pp. 4510–4520.
Wang, Wang, Zhang (b0205) 2021; 2021
Nguyen, Proença, Alonso-Fernandez (b0025) 2024; 56
M. Tan, Q. Le, EfficientNetV2: Smaller models and faster training[C], in: Proceedings of the 38th International Conference on Machine Learning (PMLR), 2021, pp. 10096–10106.
Fathee, Sahmoud (b0020) 2021; 118
A.R. Kiruthiga, R. Arumuganathan, Smoothening of iris images and pupil segmentation using fractional derivative and wavelet transform[C], in: Proceedings of the 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN). 2017, pp. 1–6.
Muhammad, Wang, Wang (b0165) 2023; 18
Z. Liu, Y. Wang, S. Vaidya, et al., KAN: Kolmogorov-arnold networks[J]. arXiv preprint arXiv:2404.19756, 2024.
Wang, Xia, Yan (b0195) 2025; 175
Sun, Lu, Liu (b0155) 2022; 2022
Chen, Gan, Zeng (b0060) 2022; 37
Kong, Zhang, Wang (b0030) 2024; 51
Z. Liu, Y. Lin, Y. Cao, et al., Swin transformer: Hierarchical vision transformer using shifted windows[C], in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 10012–10022.
T. Chen, L. Zhu, C. Deng, et al., SAM-Adapter: Adapting segment anything in underperformed scenes[C], in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2023) 3367–3375.
Chen, Gan, Chen (b0065) 2023; 517
A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al., An image is worth 16×16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020.
Y. Yuan, K.W. Bowyer, A siamese network to detect if two iris images are monozygotic[J]. arXiv preprint arXiv:2503.09749, 2025.
Jayadev, Bellary (b0175) 2024; 7
Chen, Zhu, Papandreou (b0120) 2018
O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional networks for biomedical image segmentation[C], Proceedings of the International Conference on Medical image computing and computer-assisted intervention, 2015, pp. 234–241.
Guo, Chen, Xu (b0200) 2025; 113334
Wei, Wang, Gao (b0075) 2024; 19
Woo, Park, Lee (b0220) 2018
10.1016/j.displa.2025.103192_b0215
10.1016/j.displa.2025.103192_b0115
Wang (10.1016/j.displa.2025.103192_b0145) 2020; 15
10.1016/j.displa.2025.103192_b0035
Chen (10.1016/j.displa.2025.103192_b0060) 2022; 37
10.1016/j.displa.2025.103192_b0210
10.1016/j.displa.2025.103192_b0135
Pan (10.1016/j.displa.2025.103192_b0045) 2021; 33
Woo (10.1016/j.displa.2025.103192_b0220) 2018
Wang (10.1016/j.displa.2025.103192_b0205) 2021; 2021
10.1016/j.displa.2025.103192_b0090
Sun (10.1016/j.displa.2025.103192_b0005) 2021; 26
Sun (10.1016/j.displa.2025.103192_b0150) 2022; 31
Liu (10.1016/j.displa.2025.103192_b0160) 2023; 53
Samarin (10.1016/j.displa.2025.103192_b0185) 2024; 34
Sun (10.1016/j.displa.2025.103192_b0155) 2022; 2022
Wang (10.1016/j.displa.2025.103192_b0195) 2025; 175
Khaki (10.1016/j.displa.2025.103192_b0080) 2024; 24
Yan (10.1016/j.displa.2025.103192_b0170) 2024; 30
Yin (10.1016/j.displa.2025.103192_b0015) 2025
10.1016/j.displa.2025.103192_b0110
10.1016/j.displa.2025.103192_b0010
10.1016/j.displa.2025.103192_b0230
10.1016/j.displa.2025.103192_b0095
10.1016/j.displa.2025.103192_b0050
10.1016/j.displa.2025.103192_b0225
Wei (10.1016/j.displa.2025.103192_b0075) 2024; 19
He (10.1016/j.displa.2025.103192_b0190) 2025; 55
Chen (10.1016/j.displa.2025.103192_b0065) 2023; 517
Pourafkham (10.1016/j.displa.2025.103192_b0100) 2024
Jiang (10.1016/j.displa.2025.103192_b0130) 2025; 14
Jan (10.1016/j.displa.2025.103192_b0055) 2024; 83
Guo (10.1016/j.displa.2025.103192_b0200) 2025; 113334
Kong (10.1016/j.displa.2025.103192_b0030) 2024; 51
Fathee (10.1016/j.displa.2025.103192_b0020) 2021; 118
Chen (10.1016/j.displa.2025.103192_b0120) 2018
Jayadev (10.1016/j.displa.2025.103192_b0175) 2024; 7
Daugman (10.1016/j.displa.2025.103192_b0040) 2004; 14
10.1016/j.displa.2025.103192_b0085
10.1016/j.displa.2025.103192_b0140
Guo (10.1016/j.displa.2025.103192_b0070) 2022
Bonyani (10.1016/j.displa.2025.103192_b0105) 2024; 15
10.1016/j.displa.2025.103192_b0180
Avhad (10.1016/j.displa.2025.103192_b0125) 2025; 105
Muhammad (10.1016/j.displa.2025.103192_b0165) 2023; 18
Nguyen (10.1016/j.displa.2025.103192_b0025) 2024; 56
References_xml – reference: A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al., An image is worth 16×16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020.
– volume: 33
  year: 2021
  ident: b0045
  article-title: Iris location method based on mathematical morphology and improved hough transform[J]
  publication-title: Biomed. Eng.: Appl., Basis Commun.
– volume: 14
  start-page: 246
  year: 2025
  ident: b0130
  article-title: SAM-Iris: a SAM-based iris segmentation algorithm[J]
  publication-title: Electronics
– reference: L. Yang, R.Y. Zhang, L. Li, et al., SimAM: A simple, parameter-free attention module for convolutional neural networks[C], in: Proceedings of the 38th International Conference on Machine Learning (PMLR). 2021, 139: 11863-11874.
– volume: 56
  start-page: 1
  year: 2024
  end-page: 35
  ident: b0025
  article-title: Deep learning for iris recognition: a survey[J]
  publication-title: ACM Comput. Surv.
– reference: A.R. Kiruthiga, R. Arumuganathan, Smoothening of iris images and pupil segmentation using fractional derivative and wavelet transform[C], in: Proceedings of the 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN). 2017, pp. 1–6.
– volume: 34
  start-page: 855
  year: 2024
  end-page: 862
  ident: b0185
  article-title: Segmentation of the iris and pupil of the human eye in images from an infrared camera[J]
  publication-title: Pattern Recognit Image Anal.
– volume: 53
  start-page: 11267
  year: 2023
  end-page: 11281
  ident: b0160
  article-title: IrisST-Net for iris segmentation and contour parameters extraction[J]
  publication-title: Appl. Intell.
– volume: 15
  start-page: 2944
  year: 2020
  end-page: 2959
  ident: b0145
  article-title: Towards complete and accurate iris segmentation using deep multi-task attention network for non-cooperative iris recognition[J]
  publication-title: IEEE Trans. Inf. Forensics Secur.
– volume: 7
  start-page: 41
  year: 2024
  end-page: 54
  ident: b0175
  article-title: IrisSeg-drunk: enhanced iris segmentation and classification of drunk individuals using modified circle hough transform[J]
  publication-title: Iran J. Comput. Sci.
– volume: 51
  start-page: 186
  year: 2024
  end-page: 197
  ident: b0030
  article-title: Review of heterogeneous iris recognition[J]
  publication-title: Comput. Sci.
– volume: 113334
  year: 2025
  ident: b0200
  article-title: Multiscale attention feature deep fusion network for iris region localization and segmentation from dual-spectral iris image[J]
  publication-title: Appl. Soft Comput.
– volume: 30
  start-page: 85
  year: 2024
  ident: b0170
  article-title: Iris-LAHNet: a lightweight attention-guided high-resolution network for iris segmentation and localization[J]
  publication-title: Multimedia Syst.
– reference: T. Chen, L. Zhu, C. Deng, et al., SAM-Adapter: Adapting segment anything in underperformed scenes[C], in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2023) 3367–3375.
– reference: O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional networks for biomedical image segmentation[C], Proceedings of the International Conference on Medical image computing and computer-assisted intervention, 2015, pp. 234–241.
– start-page: 1
  year: 2024
  end-page: 22
  ident: b0100
  article-title: ES-Net: UNet-based model for the semantic segmentation of iris[J]
  publication-title: Multimed. Tools Appl.
– reference: Z. Liu, Y. Lin, Y. Cao, et al., Swin transformer: Hierarchical vision transformer using shifted windows[C], in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 10012–10022.
– reference: J. Hu, L. Shen, G. Sun, Squeeze‐and‐excitation networks[C], in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
– reference: K. He, X. Zhang, S. Ren, et al., Deep residual learning for image recognition[C], in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
– reference: S. Zhang, S. Zhang, Improved three-dimensional gaze estimation with precise iris segmentation based on YOLOv8[C], in: Proceedings of the 2024 36th Chinese Control and Decision Conference (CCDC), 2024, pp. 1970–1974.
– volume: 517
  start-page: 264
  year: 2023
  end-page: 278
  ident: b0065
  article-title: Accurate iris segmentation and recognition using an end-to-end unified framework based on MADNet and DSANet[J]
  publication-title: Neurocomputing
– reference: Y. Yuan, K.W. Bowyer, A siamese network to detect if two iris images are monozygotic[J]. arXiv preprint arXiv:2503.09749, 2025.
– reference: M. Tan, Q. Le, EfficientNetV2: Smaller models and faster training[C], in: Proceedings of the 38th International Conference on Machine Learning (PMLR), 2021, pp. 10096–10106.
– volume: 37
  start-page: 829
  year: 2022
  end-page: 858
  ident: b0060
  article-title: DADCNet: dual attention densely connected network for more accurate real iris region segmentation[J]
  publication-title: Int. J.Intell. Syst.
– start-page: 801
  year: 2018:
  end-page: 818
  ident: b0120
  article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation[C]
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– volume: 31
  year: 2022
  ident: b0150
  article-title: LiSeNet: Multitask lightweight segmentation network for accurate and complete iris segmentation[J]
  publication-title: J. Electron. Imaging
– reference: Z. Liu, Y. Wang, S. Vaidya, et al., KAN: Kolmogorov-arnold networks[J]. arXiv preprint arXiv:2404.19756, 2024.
– volume: 105
  year: 2025
  ident: b0125
  article-title: An advanced deep learning model for iridology based disease diagnosis using pyramid network driven iris segmentation[J]
  publication-title: Biomed. Signal Process. Control
– volume: 19
  start-page: 6015
  year: 2024
  end-page: 6027
  ident: b0075
  article-title: Multi-faceted knowledge-driven graph neural network for iris segmentation[J]
  publication-title: IEEE Trans. Inf. Forensics Secur.
– reference: A. Hossain, T. Sultan, S. Schuckers, Post-mortem human iris segmentation analysis with deep learning[J], 2024. arXiv preprint arXiv:2408.03448.
– volume: 118
  year: 2021
  ident: b0020
  article-title: Iris segmentation in uncooperative and unconstrained environments: state-of-the-art, datasets and future research directions[J]
  publication-title: Digital Signal Process.
– start-page: 404
  year: 2022:
  end-page: 413
  ident: b0070
  article-title: Attention skip connection dense network for accurate iris segmentation[C]
  publication-title: Proceedings of the Chinese Conference on Biometric Recognition (CCBR)
– volume: 18
  start-page: 2723
  year: 2023
  end-page: 2736
  ident: b0165
  article-title: IrisGuideNet: Guided localization and segmentation network for unconstrained iris biometrics[J]
  publication-title: IEEE Trans. Inf. Forensics Secur.
– volume: 2021
  start-page: 1
  year: 2021
  end-page: 10
  ident: b0205
  article-title: NIR iris challenge evaluation in non-cooperative environments: segmentation and localization[C]
  publication-title: Proceedings of the IEEE International Joint Conference on Biometrics (IJCB).
– volume: 24
  year: 2024
  ident: b0080
  article-title: Robust convolutional neural network based on UNet for iris segmentation[J]
  publication-title: Int. J. Image Graph.
– volume: 14
  start-page: 21
  year: 2004
  end-page: 30
  ident: b0040
  article-title: How iris recogniton works[J]
  publication-title: IEEE Trans. Cricuits Syst. Video Technol.
– volume: 15
  start-page: 5239
  year: 2024
  end-page: 5255
  ident: b0105
  article-title: Different gaze direction (DGNet) collaborative learning for iris segmentation[J]
  publication-title: Int. J. Mach. Learn. Cybern.
– volume: 83
  start-page: 15223
  year: 2024
  end-page: 15251
  ident: b0055
  article-title: Iris segmentation for non-ideal iris biometric systems[J]
  publication-title: Multimed. Tools Appl.
– volume: 55
  start-page: 1
  year: 2025
  end-page: 18
  ident: b0190
  article-title: ISL-Net: dual-stream interaction network with task-optimized modules for more accurate, complete iris segmentation and localization[J]
  publication-title: Appl. Intell.
– start-page: 1
  year: 2025
  end-page: 49
  ident: b0015
  article-title: Deep learning for iris recognition: a review[J]
  publication-title: Neural Comput. & Applic.
– reference: M. Sandler, A. Howard, M. Zhu, et al., MobileNetV2: Inverted residuals and linear bottlenecks[C], in: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2018, pp. 4510–4520.
– volume: 175
  year: 2025
  ident: b0195
  article-title: A light spatial-frequency network for robust iris segmentation and localization[J]
  publication-title: Appl. Soft Comput.
– volume: 26
  start-page: 1254
  year: 2021
  end-page: 1329
  ident: b0005
  article-title: Overview of biometrics research[J]
  publication-title: J. Image Graph.
– reference: Z. Jia, J. Deng, L. Chi, et al., CondSeg: Ellipse estimation of pupil and iris via conditioned segmentation[J]. arXiv preprint arXiv:2408.17231, 2024.
– volume: 2022
  start-page: 1
  year: 2022
  end-page: 10
  ident: b0155
  article-title: Towards more accurate and complete iris segmentation using hybrid transformer U-Net[C]//Proceedings of the
  publication-title: IEEE Int. Joint Conf. Biometrics (IJCB).
– start-page: 3
  year: 2018:
  end-page: 19
  ident: b0220
  article-title: CBAM: Convolutional block attention module[C]
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– volume: 53
  start-page: 11267
  issue: 9
  year: 2023
  ident: 10.1016/j.displa.2025.103192_b0160
  article-title: IrisST-Net for iris segmentation and contour parameters extraction[J]
  publication-title: Appl. Intell.
  doi: 10.1007/s10489-022-03973-8
– ident: 10.1016/j.displa.2025.103192_b0215
  doi: 10.1109/ICCV48922.2021.00986
– volume: 26
  start-page: 1254
  issue: 6
  year: 2021
  ident: 10.1016/j.displa.2025.103192_b0005
  article-title: Overview of biometrics research[J]
  publication-title: J. Image Graph.
  doi: 10.11834/jig.210078
– volume: 14
  start-page: 246
  issue: 2
  year: 2025
  ident: 10.1016/j.displa.2025.103192_b0130
  article-title: SAM-Iris: a SAM-based iris segmentation algorithm[J]
  publication-title: Electronics
  doi: 10.3390/electronics14020246
– ident: 10.1016/j.displa.2025.103192_b0140
  doi: 10.1109/ICCVW60793.2023.00361
– volume: 7
  start-page: 41
  issue: 1
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0175
  article-title: IrisSeg-drunk: enhanced iris segmentation and classification of drunk individuals using modified circle hough transform[J]
  publication-title: Iran J. Comput. Sci.
  doi: 10.1007/s42044-023-00157-6
– volume: 15
  start-page: 5239
  issue: 11
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0105
  article-title: Different gaze direction (DGNet) collaborative learning for iris segmentation[J]
  publication-title: Int. J. Mach. Learn. Cybern.
  doi: 10.1007/s13042-024-02232-1
– volume: 517
  start-page: 264
  year: 2023
  ident: 10.1016/j.displa.2025.103192_b0065
  article-title: Accurate iris segmentation and recognition using an end-to-end unified framework based on MADNet and DSANet[J]
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2022.10.064
– start-page: 801
  year: 2018
  ident: 10.1016/j.displa.2025.103192_b0120
  article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation[C]
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– volume: 37
  start-page: 829
  issue: 1
  year: 2022
  ident: 10.1016/j.displa.2025.103192_b0060
  article-title: DADCNet: dual attention densely connected network for more accurate real iris region segmentation[J]
  publication-title: Int. J.Intell. Syst.
  doi: 10.1002/int.22649
– volume: 30
  start-page: 85
  issue: 2
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0170
  article-title: Iris-LAHNet: a lightweight attention-guided high-resolution network for iris segmentation and localization[J]
  publication-title: Multimedia Syst.
  doi: 10.1007/s00530-024-01280-5
– ident: 10.1016/j.displa.2025.103192_b0095
  doi: 10.1109/CCDC62350.2024.10588166
– ident: 10.1016/j.displa.2025.103192_b0210
– volume: 113334
  year: 2025
  ident: 10.1016/j.displa.2025.103192_b0200
  article-title: Multiscale attention feature deep fusion network for iris region localization and segmentation from dual-spectral iris image[J]
  publication-title: Appl. Soft Comput.
– start-page: 404
  year: 2022
  ident: 10.1016/j.displa.2025.103192_b0070
  article-title: Attention skip connection dense network for accurate iris segmentation[C]
  publication-title: Proceedings of the Chinese Conference on Biometric Recognition (CCBR)
  doi: 10.1007/978-3-031-20233-9_41
– volume: 55
  start-page: 1
  issue: 6
  year: 2025
  ident: 10.1016/j.displa.2025.103192_b0190
  article-title: ISL-Net: dual-stream interaction network with task-optimized modules for more accurate, complete iris segmentation and localization[J]
  publication-title: Appl. Intell.
– volume: 33
  issue: 01
  year: 2021
  ident: 10.1016/j.displa.2025.103192_b0045
  article-title: Iris location method based on mathematical morphology and improved hough transform[J]
  publication-title: Biomed. Eng.: Appl., Basis Commun.
– volume: 83
  start-page: 15223
  issue: 5
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0055
  article-title: Iris segmentation for non-ideal iris biometric systems[J]
  publication-title: Multimed. Tools Appl.
  doi: 10.1007/s11042-021-11075-9
– ident: 10.1016/j.displa.2025.103192_b0225
– ident: 10.1016/j.displa.2025.103192_b0085
  doi: 10.1007/978-3-319-24574-4_28
– volume: 2021
  start-page: 1
  year: 2021
  ident: 10.1016/j.displa.2025.103192_b0205
  article-title: NIR iris challenge evaluation in non-cooperative environments: segmentation and localization[C]
  publication-title: Proceedings of the IEEE International Joint Conference on Biometrics (IJCB).
– volume: 24
  issue: 04
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0080
  article-title: Robust convolutional neural network based on UNet for iris segmentation[J]
  publication-title: Int. J. Image Graph.
  doi: 10.1142/S0219467824500426
– volume: 105
  year: 2025
  ident: 10.1016/j.displa.2025.103192_b0125
  article-title: An advanced deep learning model for iridology based disease diagnosis using pyramid network driven iris segmentation[J]
  publication-title: Biomed. Signal Process. Control
  doi: 10.1016/j.bspc.2025.107595
– ident: 10.1016/j.displa.2025.103192_b0110
– volume: 15
  start-page: 2944
  year: 2020
  ident: 10.1016/j.displa.2025.103192_b0145
  article-title: Towards complete and accurate iris segmentation using deep multi-task attention network for non-cooperative iris recognition[J]
  publication-title: IEEE Trans. Inf. Forensics Secur.
  doi: 10.1109/TIFS.2020.2980791
– start-page: 3
  year: 2018
  ident: 10.1016/j.displa.2025.103192_b0220
  article-title: CBAM: Convolutional block attention module[C]
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– volume: 118
  year: 2021
  ident: 10.1016/j.displa.2025.103192_b0020
  article-title: Iris segmentation in uncooperative and unconstrained environments: state-of-the-art, datasets and future research directions[J]
  publication-title: Digital Signal Process.
  doi: 10.1016/j.dsp.2021.103244
– ident: 10.1016/j.displa.2025.103192_b0050
  doi: 10.1109/ICSCN.2017.8085713
– ident: 10.1016/j.displa.2025.103192_b0135
– start-page: 1
  year: 2025
  ident: 10.1016/j.displa.2025.103192_b0015
  article-title: Deep learning for iris recognition: a review[J]
  publication-title: Neural Comput. & Applic.
– volume: 31
  issue: 5
  year: 2022
  ident: 10.1016/j.displa.2025.103192_b0150
  article-title: LiSeNet: Multitask lightweight segmentation network for accurate and complete iris segmentation[J]
  publication-title: J. Electron. Imaging
  doi: 10.1117/1.JEI.31.5.053035
– ident: 10.1016/j.displa.2025.103192_b0180
  doi: 10.1007/978-3-031-91989-3_12
– volume: 18
  start-page: 2723
  year: 2023
  ident: 10.1016/j.displa.2025.103192_b0165
  article-title: IrisGuideNet: Guided localization and segmentation network for unconstrained iris biometrics[J]
  publication-title: IEEE Trans. Inf. Forensics Secur.
  doi: 10.1109/TIFS.2023.3268504
– volume: 19
  start-page: 6015
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0075
  article-title: Multi-faceted knowledge-driven graph neural network for iris segmentation[J]
  publication-title: IEEE Trans. Inf. Forensics Secur.
  doi: 10.1109/TIFS.2024.3407508
– ident: 10.1016/j.displa.2025.103192_b0115
  doi: 10.1109/CVPR.2018.00474
– ident: 10.1016/j.displa.2025.103192_b0230
  doi: 10.1109/CVPR.2018.00745
– ident: 10.1016/j.displa.2025.103192_b0090
  doi: 10.1109/CVPR.2016.90
– ident: 10.1016/j.displa.2025.103192_b0010
– volume: 56
  start-page: 1
  issue: 9
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0025
  article-title: Deep learning for iris recognition: a survey[J]
  publication-title: ACM Comput. Surv.
  doi: 10.1145/3651306
– start-page: 1
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0100
  article-title: ES-Net: UNet-based model for the semantic segmentation of iris[J]
  publication-title: Multimed. Tools Appl.
– ident: 10.1016/j.displa.2025.103192_b0035
– volume: 34
  start-page: 855
  issue: 3
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0185
  article-title: Segmentation of the iris and pupil of the human eye in images from an infrared camera[J]
  publication-title: Pattern Recognit Image Anal.
  doi: 10.1134/S1054661824700743
– volume: 175
  year: 2025
  ident: 10.1016/j.displa.2025.103192_b0195
  article-title: A light spatial-frequency network for robust iris segmentation and localization[J]
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2025.113009
– volume: 14
  start-page: 21
  issue: 1
  year: 2004
  ident: 10.1016/j.displa.2025.103192_b0040
  article-title: How iris recogniton works[J]
  publication-title: IEEE Trans. Cricuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2003.818350
– volume: 51
  start-page: 186
  issue: 06
  year: 2024
  ident: 10.1016/j.displa.2025.103192_b0030
  article-title: Review of heterogeneous iris recognition[J]
  publication-title: Comput. Sci.
– volume: 2022
  start-page: 1
  year: 2022
  ident: 10.1016/j.displa.2025.103192_b0155
  article-title: Towards more accurate and complete iris segmentation using hybrid transformer U-Net[C]//Proceedings of the
  publication-title: IEEE Int. Joint Conf. Biometrics (IJCB).
SSID ssj0002472
Score 2.4072304
Snippet •Proposed a cascade attention feature residual fusion network (CA-RFNet).•Deep convolutional residual blocks in the encoder to enhance feature representation...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 103192
SubjectTerms Boundary perception module
CA-RFNet
Cascade attention fusion module
Deep convolutional residual block
Iris localization and segmentation
Title Cascade attention feature residual fusion network for iris localization and segmentation in non-cooperative environments
URI https://dx.doi.org/10.1016/j.displa.2025.103192
Volume 91
WOSCitedRecordID wos001563420500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect (Freedom Collection)
  issn: 0141-9382
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0002472
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLfKxgEOaHyJAUM-cKsyNZnt2MepjG0ITUgMqZwix7EhW0mrtZnKlb-c5680ZWhiBy5RZDmO4_fze88v7wOhtyNRKipK2Eg5FQnI6zThFZxatSpHqRacEO2SuH7Mz874ZCI-DQa_YizM9TRvGr5aifl_JTW0AbFt6OwdyN0NCg1wD0SHK5Adrv9E-LFcWJ_3oU2c6V0ZjXbZO4dwsvahV6a1NrJh413AnadhDZt96ARbCMx0fxUW-tuPEJzkPCKbWZOo2WyuQ77wfphcX819Vy_mU_mz09ePW2eR_fy9LesOjeMQGPI1Sk-rT-vgIdw2l3LdHLuetPU09g6miqxvqojWyzQRB3yD_fpiXYF_2qITvjbeDdburQwX-5X7AjjZZ3R_3X0zk_YfEq7zO4wubReFH6WwoxR-lHtoOwO8AmfcPjw9mnzo5HlGXAmwbvIxANN5Cd6czd8VnJ7Scr6DHoXTBj70KHmMBrp5gh72clA-RauAF9zhBQe84IgX7PGCA14w4AVbvOA-XjDgBffxgmt4YhMvuI-XZ-jL-6Pz8UkSynEkCvj6MiGMUamZ4VXFGUmNDVIWMsvVSDNuYMvTihOuOKyTkVLprCSCUJAIjEhBS3rwHG3Ba_ULhDPGaU40SbUhhCgmDWGi1Cw1FSiwcrSLkriGxdxnXSluo90uyuNCF0Fz9BphAei59cmXd3zTK_RgjezXaGt51eo9dF9dL-vF1ZsAnd_cnpaN
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Cascade+attention+feature+residual+fusion+network+for+iris+localization+and+segmentation+in+non-cooperative+environments&rft.jtitle=Displays&rft.au=Guo%2C+Shubin&rft.au=Chen%2C+Ying&rft.au=Deng%2C+Junkang&rft.au=Chen%2C+Huiling&rft.date=2026-01-01&rft.issn=0141-9382&rft.volume=91&rft.spage=103192&rft_id=info:doi/10.1016%2Fj.displa.2025.103192&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_displa_2025_103192
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0141-9382&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0141-9382&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0141-9382&client=summon