Advanced Search
Article Contents
Article Contents

Two-hidden-layer extreme learning machine based wrist vein recognition system

The first author is supported by National Natural Science Foundation of China (61473266,61673404,61305080, and U1304602).
Abstract Full Text(HTML) Figure(9) / Table(2) Related Papers Cited by
  • Vein recognition is a new identity authentication technology. It attracts many researchers' attention due to its good security and reliability. This paper proposes a wrist vein recognition system. The proposed system identifies people according to the characteristics of their wrist veins. A special camera is reformed to obtain the wrist vein images and an image dataset is established. Principal component analysis (PCA) is adopted to eliminate the redundant information in the images and extract their global features. The global features are classified by Two-hidden-layer Extreme Learning Machine (TELM). TELM is compared with original Extreme Learning Machine (ELM) and other two algorithms Support Vector Machine (SVM) and Naive Bayes (NB). Experiment results show that the accuracy of the proposed system is higher than the other three algorithms. Though the speed of TELM is not the fastest, it is able to recognize images within satisfactory time.

    Mathematics Subject Classification: Primary: 68T10; Secondary: 68U10.


    \begin{equation} \\ \end{equation}
  • 加载中
  • Figure 1.  The flow chat of the wrist vein recognition system

    Figure 2.  Transmitting of light

    Figure 3.  The obtained wrist vein images

    Figure 4.  Regions of interest

    Figure 5.  Histogram comparison between original and transformed images

    Figure 6.  Comparison between original and transformed images

    Figure 7.  Workflow of TELM

    Figure 8.  Network structure of TELM

    Figure 9.  The comparison of TELM and ELM

    Table 1.  The performance of TELM with and without gray normalization

    TELM with gray normalization TELM without gray normalization
    99.58±0.0671% 94.39±0.4271%
     | Show Table
    DownLoad: CSV

    Table 2.  Performances of different algorithms

    Algorithm name Accuracy (%) Ttraining(ms) Ttesting(ms) FRR FAR
     | Show Table
    DownLoad: CSV
  • [1] T. ChenJ. Cai and L. Guo, Research on hybrid face recognition algorithm based on voting Extreme Learning Machine, Journal of Zhengzhou University (Engineering Science), 37 (2016), 37-41. 
    [2] J. M. Cross and C. L. Smith, Thermographic imaging of the subcutaneous vascular network of the back of the hand for biometric identification, Institute of Electrical and Electronics Engineers Conference on Security Technology, (1995), 20-35.  doi: 10.1109/CCST.1995.524729.
    [3] S. DongJ. Yang and Y. Chen, Finger vein recognition based on multi-orientation weighted symmetric local graph structure, KSII Transactions on Internet and Information Systems, 9 (2015), 4126-4142. 
    [4] J. Hashimoto, Finger vein authentication technology and its future, Symposium on VLSI Circuits, (2006), 5-8.  doi: 10.1109/VLSIC.2006.1705285.
    [5] C. B. HsuS. S. Hao and J. C. Lee, Personal authentication through dorsal hand vein patterns, Optical Engineering, 50 (2011), 087201, 10pp.  doi: 10.1117/1.3607413.
    [6] G. B. HuangQ. Y. Zhu and C. K. Siew, Extreme learning machine: Theory and applications, Neurocomputing, 70 (2006), 489-501.  doi: 10.1016/j.neucom.2005.12.126.
    [7] S. K. ImH. M. Park and Y. W. Kim, An biometric identification system by extracting hand vein patterns, Journal-korean Physical Society, 3 (2001), 268-272. 
    [8] M. KonoH. Ueki and S. I. Umemura, A new method for the identification of individuals by using of vein pattern matching of a finger, The Fifth Symposium on Pattern Mea-surement, (2000), 9-12. 
    [9] A. Kumar and K. V. Prathyusha, Personal authentication using hand vein triangulation and knuckle shape, IEEE Transactions on Image processing, 18 (2009), 2127-2136.  doi: 10.1109/TIP.2009.2023153.
    [10] X. LiS. Guo and F. Gao, Vein pattern recognitions by moment invariants, Bioinformatics and Biomedical Engineering, (2007), 612-615.  doi: 10.1109/ICBBE.2007.160.
    [11] D. Mulyono and H. S. Jinn, A study of finger vein biometric for personal identification, International Symposium on Biometrics and Security Technologies, (2008), 1-8.  doi: 10.1109/ISBAST.2008.4547655.
    [12] B. Y. QuB. F. Lang and J. J. Liang, Two-hidden-layer extreme learning machine for regression and classification, Neurocomputing, 175 (2016), 826-834.  doi: 10.1016/j.neucom.2015.11.009.
    [13] N. SugandhiM. Mathankumar and V. Priya, Real time authentication system using advanced finger vein recognition technique, International Conference on Communications and Signal Processing, (2014), 1183-1187. 
    [14] J. WangQ. Chang and J. Peng, The Optimization of the Extreme Learning Machine and fitting analysis, Journal of Zhengzhou University (Engineering Science), 37 (2016), 20-24. 
    [15] L. Wang and G. Leedham, Near and far infrared imaging for vein pattern biometrics, Video and Signal Based Surveillance, (2006), 52-58.  doi: 10.1109/AVSS.2006.80.
    [16] Y. WangK. Li and J. Cui, Hand-dorsa vein recognition based on partition local binary pattern, IEEE 10th International Conference on Signal Processing, (2010), 1671-1674.  doi: 10.1109/ICOSP.2010.5656717.
    [17] K. S. WuJ. C. Lee and T. M. Lo, A secure palm vein recognition system, Journal of Systems and Software, 86 (2013), 2870-2876.  doi: 10.1016/j.jss.2013.06.065.
    [18] J. Yang and X. Li, Efficient finger vein localization and recognition, Pattern Recognition, (2010), 1148-1151.  doi: 10.1109/ICPR.2010.287.
    [19] W. YangX. Huang and F. Zhou, Comparative competitive coding for personal identification by using finger vein and finger dorsal texture fusion, Information Sciences, 268 (2014), 20-32.  doi: 10.1016/j.ins.2013.10.010.
  • 加载中




Article Metrics

HTML views(350) PDF downloads(157) Cited by(0)

Access History

Other Articles By Authors



    DownLoad:  Full-Size Img  PowerPoint