Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module

Hand vein image segmentation is crucial for diverse applications such as precise biometric identification and facilitating medical intravenous procedures. This paper introduces an enhanced hand vein image segmentation method utilizing deep learning, specifically a conditional generative adversarial...

Full description

Bibliographic Details
Main Authors: Marlina, Yakno, Mohd Zamri, Ibrahim, Muhammad Salihin, Saealal, Norasyikin, Fadilah, Wan Nur Azhani, Wan Samsudin
Format: Article
Language:English
Published: ECTI Association 2025
Subjects:
Online Access:https://umpir.ump.edu.my/id/eprint/44346/
_version_ 1848827326893129728
author Marlina, Yakno
Mohd Zamri, Ibrahim
Muhammad Salihin, Saealal
Norasyikin, Fadilah
Wan Nur Azhani, Wan Samsudin
author_facet Marlina, Yakno
Mohd Zamri, Ibrahim
Muhammad Salihin, Saealal
Norasyikin, Fadilah
Wan Nur Azhani, Wan Samsudin
author_sort Marlina, Yakno
building UMP Institutional Repository
collection Online Access
description Hand vein image segmentation is crucial for diverse applications such as precise biometric identification and facilitating medical intravenous procedures. This paper introduces an enhanced hand vein image segmentation method utilizing deep learning, specifically a conditional generative adversarial network (cGAN). The cGAN is trained adversarially and augmented with a modied ecient channel attention (ECA) mechanism module. The efficiency of the proposed technique was evaluated using four hand vein datasets: self-acquired dataset, SUAS, WILCHES, and BOSPHORUS. Performance comparison reveals that the proposed method outperforms alternative approaches, achieving the best results across all datasets with an average sensitivity of 0.8878, average accuracy of 0.9639, and average dice coeffcient of 0.7904 for vein patterns. Our experimental findings demonstrate that the proposed segmentation technique significantly enhances hand vein patterns and improves dorsal hand vein detection accuracy.
first_indexed 2025-11-15T03:58:57Z
format Article
id ump-44346
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:58:57Z
publishDate 2025
publisher ECTI Association
recordtype eprints
repository_type Digital Repository
spelling ump-443462025-08-28T00:18:15Z https://umpir.ump.edu.my/id/eprint/44346/ Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module Marlina, Yakno Mohd Zamri, Ibrahim Muhammad Salihin, Saealal Norasyikin, Fadilah Wan Nur Azhani, Wan Samsudin QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering Hand vein image segmentation is crucial for diverse applications such as precise biometric identification and facilitating medical intravenous procedures. This paper introduces an enhanced hand vein image segmentation method utilizing deep learning, specifically a conditional generative adversarial network (cGAN). The cGAN is trained adversarially and augmented with a modied ecient channel attention (ECA) mechanism module. The efficiency of the proposed technique was evaluated using four hand vein datasets: self-acquired dataset, SUAS, WILCHES, and BOSPHORUS. Performance comparison reveals that the proposed method outperforms alternative approaches, achieving the best results across all datasets with an average sensitivity of 0.8878, average accuracy of 0.9639, and average dice coeffcient of 0.7904 for vein patterns. Our experimental findings demonstrate that the proposed segmentation technique significantly enhances hand vein patterns and improves dorsal hand vein detection accuracy. ECTI Association 2025-04 Article PeerReviewed pdf en cc_by_nc_nd_4 https://umpir.ump.edu.my/id/eprint/44346/1/Enhanced%20hand%20vein%20segmentation%20using%20generative%20adversarial%20network.pdf Marlina, Yakno and Mohd Zamri, Ibrahim and Muhammad Salihin, Saealal and Norasyikin, Fadilah and Wan Nur Azhani, Wan Samsudin (2025) Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module. ECTI Transactions on Computer and Information Technology, 19 (2). pp. 182-194. ISSN 2286-9131. (Published) https://doi.org/10.37936/ecti-cit.2025192.259390 https://doi.org/10.37936/ecti-cit.2025192.259390 https://doi.org/10.37936/ecti-cit.2025192.259390
spellingShingle QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
Marlina, Yakno
Mohd Zamri, Ibrahim
Muhammad Salihin, Saealal
Norasyikin, Fadilah
Wan Nur Azhani, Wan Samsudin
Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module
title Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module
title_full Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module
title_fullStr Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module
title_full_unstemmed Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module
title_short Enhanced hand vein segmentation using generative adversarial network integrated with modified ECA module
title_sort enhanced hand vein segmentation using generative adversarial network integrated with modified eca module
topic QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
url https://umpir.ump.edu.my/id/eprint/44346/
https://umpir.ump.edu.my/id/eprint/44346/
https://umpir.ump.edu.my/id/eprint/44346/