Fully automated human finger vein binary pattern extraction-based double optimization stages of unsupervised learning approach

Document Type : Research Paper


Department of Computer Science, College of Science, University of Diyala, Baquba, Iraq


Today, finger vein identification is gaining popularity as a potential biometric identification framework solution. Machine learning-based unsupervised supervised, and deep learning algorithms have had a significant influence on finger vein detection and recognition at the moment. Deep learning, on the other hand, necessitates a large number of training datasets that must be manually produced and labelled. In this research, we offer a completely automated unsupervised learning strategy for training dataset creation. Our method is intended to extract and build a decent binary mask training dataset completely automatically. In this technique, two optimization steps are devised and employed. The initial stage of optimization is to create a completely automated unsupervised image clustering based on finger vein image localization. In the second optimization, the retrieved finger vein lines are optimized. Lastly, the proposed system has a pattern extraction accuracy of 99.6\%, which is much higher than other common unsupervised learning methods like k-means and Fuzzy C-Means (FCM).


[1] A. Al-Azzawi, T.X. Han, D. Al-Jumeily, J. Hind and A. Mahdi, A robust spatially invariant model for latent
fingerprint authentication approach, 10th Int. Conf. Dev. Syst. Engin. (DeSE), IEEE, 2017, pp. 94–99.
[2] M.K. Chung, Gaussian kernel smoothing, arXiv preprint arXiv:2007.09539, (2012).
[3] R.C. Gonzalez and R.E. Woods, Digital image processing, Pearson, 2016.
[4] B. Huang, Y. Dai, R. Li, D. Tang and W. Li, Finger-vein authentication based on wide line detector and pattern
normalization, 20th Int. Conf. Pattern Recognit. (ICPR), Istanbul, Turkey, 2010, pp. 1269–1272.
[5] A. Kumar and Y. Zhou, Human identification using finger images, IEEE Trans. Image Process. 21 (2011), 2228–
[6] J.-W. Liu and L. Guo, Selection of initial parameters of K-means clustering algorithm for MRI brain image
segmentation, IEEE Int. Conf. Machine Learn. Cyber. 1 (2015), 123–127.
[7] Z. Liu and S. Song, An embedded real-time finger-vein recognition system for mobile devices, IEEE Trans. consumer
Electron. 58 (2012), no. 2, 522–527.
[8] M.R. Mahmood and A.M. Abdulazeez, A comparative study of a new hand recognition model based on line of
features and other techniques, Int. Conf. Reliable Inf. Commun. Technol., Springer, Cham. 2017, pp. 420–432.
[9] N. Miura, A. Nagasaka and T. Miyatake, Extraction of finger-vein patterns using maximum curvature points inimage profiles, IEICE Trans. Inf. Syst. 90 (2007), no. 8, 1185–1194.
[10] W. Song, T. Kim, H.C. Kim, J.H. Choi, H.J. Kong and S.R. Lee, A finger-vein verification system using mean
curvature, Pattern Recognit. Lett. 32 (2011), no. 11, 1541–1547.
[11] J.A. Unar, W.C. Seng and A. Abbasi, A review of biometric technology along with trends and prospects, Pattern
Recog. 47 (2014), no. 8, 2673–2688.
[12] Wikipedia, Normalization (image processing), https://en.wikipedia.org/wiki/Normalization (image processing),
[13] J. Yang and J. Wang, Finger-vein image restoration considering skin layer structure, Proc. Int. Conf. Hand-Based
Biometrics, Hong Kong, China, 2011, pp. 1–5.
[14] L. Yang, G. Yang, Y. Yin and X. Xi, Finger vein recognition with anatomy structure analysis, IEEE Trans. 28
(2018), no. 8, 1892–1905.
[15] Y. Yin, L. Liu and X. Sun, SDUMLA-HMT: a multimodal biometric database, Chinese Conf. Biometric Recog.,
Springer, Berlin, Heidelberg, 2011, pp. 260–268.
[16] C.-B. Yu, D.-M. Zhang, H.-B. Li and F. Zhang, Finger-vein image enhancement based on muti-threshold fuzzy
algorithm, Proc. Int. Cong. Image Signal Process., Tianjin, China, 2009, pp. 1–3.
[17] R. Yusoff and A.R. Ramli, Hardware efficient vein enhancement and feature extraction method, Sci. Technol. Res.
Inst. Defrence 14 (2017).
[18] D.Q. Zeebaree, H. Haron, A.M. Abdulazeez and S.R.M. Zeebaree, Combination of K-means clustering with genetic
algorithm: a review, Int. J. Appl. Eng. Res. 12 (2017), no. 24, 14238–14245.
[19] J. Zhang and J. Yang, Finger-vein image enhancement based on combination of gray-level grouping and circular
gabor filter, Proc. Int. Conf. Inf. Engin. Comput. Sci., Wuhan, China, 2009, pp. 1–4.
Volume 13, Issue 2
July 2022
Pages 2311-2323
  • Receive Date: 02 March 2022
  • Revise Date: 10 April 2022
  • Accept Date: 17 May 2022