Enhanced Hand Vein Segmentation Using Generative Adversarial Network Integrated with Modied ECA Module
Article Sidebar
Main Article Content
Abstract
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.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
N. T. Han, N. Mukahar and B. A. Rosdi, “Finger Vein Recognition Using Principle Component Analysis and Adaptive k-Nearest Centroid Neighbour Classifier,” Int. J. Integr. Eng., vol. 13, no. 1, pp. 177–187, 2021.
C. X. Jing, G. C. Meng, M. T. Chai, S. A. Z. S. Aluwee and S. A. A. Shah, “Subcutaneous Vein Recognition System Using Deep Learning for Intravenous (IV) Access Procedure,” Int. J. Integr. Eng., vol. 15, no. 3, pp. 73–83, 2023.
M. Yakno, J. Mohamad-Saleh and B. A. Rosdi, “Grayscale and binary enhancement of dorsal hand vein images,” Int. J. Circuits, Syst. Signal Process., vol. 11, pp. 129–141, 2017.
S. C. Soh, M. Z. Ibrahim and M. B. Yakno, “A review: Personal identification based on palm vein infrared pattern,” J. Telecommun. Electron. Comput. Eng., vol. 10, no. 1–4, pp. 175–180, 2018.
N. Laopracha and K. Bunluewong, “Improving the Performance of CNN by Using Dominant Patterns of CNN for Hand Detection,” ECTI Transactions on Computer and Information Technology, vol. 17, no. 2, pp. 265–277, 2023.
Y. Wang, X. Cao and X. Miao, “Cross-device recognition of dorsal hand vein images by two-stage coarse-to-fine matching,” Vis. Comput., vol. 38, no. 11, pp. 3595–3610, 2022.
Q. Yan et al., “Attention-Guided Deep Neural Network with Multi-Scale Feature Fusion for Liver Vessel Segmentation,” IEEE J. Biomed. Heal. Informatics, vol. 25, no. 7, pp. 2629–2642, 2021.
X. Li, Z. Li, D. Yang, L. Zhong, L. Huang and J. Lin, “Research on finger vein image segmentation and blood sampling point location in automatic blood collection,” Sensors, vol. 21, no. 1, pp. 1–14, 2021.
D. Zhong, H. Shao and S. Liu, “Towards application of dorsal hand vein recognition under uncontrolled environment based on biometric graph matching,” IET Biometrics, vol. 8, no. 2, pp. 159–167, 2019.
F. Marattukalam and W. H. Abdulla, “Segmentation of palm vein images using U-Net,” in Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, no. December, pp. 64–70, 2020.
S. Lefkovits and S. Emerich, “Boosting unsupervised dorsal hand vein segmentation with U-Net variants,” Mathematics, vol. 10, no. 2620, pp. 1–31, 2022.
A. Kuthiala et al., “U-DAVIS-Deep learning based arm venous image segmentation technique for venipuncture,” Comput. Intell. Neurosci., vol. 2022, pp. 1–9, 2022.
T. He, C. Guo, L. Jiang and H. Liu, “Automatic Venous Segmentation in Venipuncture Robot Using Deep Learning,” 2021 IEEE International Conference on Real-time Computing and Robotics (RCAR), Xining, China, pp. 614-619, 2021.
A. Z. Alali and K. Hussein Ali, “Segmentation of Human Brain Gliomas Tumour Images using U-Net Architecture with Transfer Learning,” Diyala J. Eng. Sci., vol. 8716, no. 1, pp. 17–29, 2022.
M. Yakno, J. Mohamad-Saleh and M. Z. Ibrahim, Dorsal Hand Vein Segmentation Using Vein-Generative Adversarial Network (V-GAN) Model, vol. 829 LNEE. Springer Singapore, 2022.
X. Gao, G. Zhang and K. Wang, “Segmentation model of dorsal hand vein based on improved U-Net,” in Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering, pp. 1361–1365, 2021.
W. Yang, C. Hui, Z. Chen, J. -H. Xue and Q. Liao, “FV-GAN: Finger Vein Representation Using Generative Adversarial Networks,” in IEEE Transactions on Information Forensics and Security, vol. 14, no. 9, pp. 2512-2524, Sept. 2019.
V. Abramova et al., “Hemorrhagic stroke lesion segmentation using a 3D U-Net with squeeze-and-excitation blocks,” Comput. Med. Imaging Graph., vol. 90, no. 101908, pp. 1–12, 2021.
S. Luan, X. Xue, Y. Ding, W. Wei and B. Zhu, “Adaptive attention convolutional neural network for liver tumor segmentation,” Front. On-col., vol. 11, pp. 1–12, 2021.
Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo and Q. Hu, “ECA-Net: Efficient channel attention for deep convolutional neural networks,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, pp. 11531–11539.
X. Shu, F. Chang, X. Zhang, C. Shao and X. Yang, “ECAU-Net: Efficient channel attention U-Net for fetal ultrasound cerebellum segmentation,” Biomed. Signal Process. Control, vol. 75, no. December 2021, p. 103528, 2022.
Y. Liu et al., “ECA-TFUnet: A U-shaped CNN-Transformer network with efficient channel attention for organ segmentation in anatomical sectional images of canines,” Math. Biosci. Eng., vol. 20, no. 10, pp. 18650–18669, 2023.
M. Yakno, J. Mohamad-Saleh, M. Z. Ibrahim and W. N. A. W. Samsudin, “Camera-projector calibration for near-infrared imaging system,” Bulletin of Electrical Engineering and Informatics, vol. 9, no. 1, pp. 160–170, 2020.
M. E. Cimen, O. F. Boyraz, M. Z. Yildiz and A. F. Boz, “A new dorsal hand vein authentication system based on fractal dimension box-counting method,” Optik (Stuttg)., vol. 226, no. P1, p. 165438, 2021.
´
F. Wilches-Bernal, B. N´u¯nez Alvares and P. Vizcaya, “A Database of Dorsal Hand Vein Images,” pp. 1–4, 2020.
O. Toygar, F. O. Babalola, and Y. Bitirim, “FYO: A novel multimodal vein database with palmar, dorsal and wrist biometrics,” IEEE Access, vol. 8, pp. 82461–82470, 2020.
M. Yakno, J. Mohamad-Saleh, M. Z. Ibrahim, S. M. Shaharum and R. Abdul-Karim, Hand Vein Region of Interest (ROI) Extraction Using Faster Region-Based Convolutional Neural Network (R-CNN), vol. 1213 LNEE. Springer Nature Singapore, 2024.
M. Yakno, J. Mohamad-Saleh and M. Z. Ibrahim, “Dorsal hand vein image enhancement using fusion of clahe and fuzzy adaptive gamma,” Sensors, vol. 21, no. 19, pp. 1–19, 2021.
X. Guo et al., “Retinal vessel segmentation combined with generative adversarial networks and Dense U-Net,” IEEE Access, vol. 8, pp. 194551–194560, 2020.
H. A. Phan et al., “Development of an Autonomous Component Testing System with Reliability Improvement Using Computer Vision and Machine Learning,” ECTI Transactions on Computer and Information Technology, vol. 18, no. 1, pp. 64–75, 2024.
D. Divya and M. Thilagu, “Region Growing based K-means Clustering and Optimal Weight Prior-Attention Residual Learning for Segmentation and Classification of COVID-19 CT Images,” ECTI Transactions on Computer and Information Technology, vol. 18, no. 1, pp. 76–88, 2024.
S. Das, M. Mishra and S. Majumder, “Identification of Glaucoma from Retinal Fundus Images using Deep Learning Model, MobileNet,” ECTI Transactions on Computer and Information Technology, vol. 18, no. 3, pp. 371–380, 2024.