Laser & Optoelectronics Progress, Volume. 58, Issue 2, 0210019(2021)

Finger-Knuckle-Print Recognition Based on NSST and Tetrolet Energy Features

Yuan Wang* and Sen Lin
Author Affiliations
  • School of Electronic and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China
  • show less
    Figures & Tables(19)
    Five basic Tetrominoes
    Flow chart of our method
    Result processed by our method. (a) Image processed by our method; (b) energy characteristic surface
    Energy difference surfaces under different conditions. (a) Image1 of the same person; (b) image2 of the same person (c) image of the different person; (d) matching energy difference surface; (e) mismatching energy difference surface
    Example of HKPU-FKP database ROI. (a) Original database; (b) noise database
    Histogram equalization contrast. (a) Image before equalization; (b) histogram before equalization; (c) image after equalization; (d) histogram after equalization
    Matching curve and ROC (HKPU-FKP and noise database). (a) Matching curve;(b) ROC
    Example of IIT Delhi-FK database. (a) Original database; (b) noise database
    Matching curve and ROC (IIT Delhi-FK and noise database). (a) Matching curve; (b) ROC
    Example of HKPU-CFK ROI database. (a) Original database; (b) noise database
    Matching curve and ROC (HKPU-CFK and noise database). (a) Matching curve; (b) ROC
    Correct recognition rate and matching time. (a) Correct recognition rate; (b) matching time
    • Table 1. Recognition rate and matching time (HKPU-FKP original database)

      View table

      Table 1. Recognition rate and matching time (HKPU-FKP original database)

      AlgorithmGabor+LDAPCAHaarLBPSurfaceletTetrolet2DPCANTES
      WCRR/%96.872194.456496.670194.265995.238196.190198.102598.0392
      Matching time/s0.14520.09870.04440.01260.15620.09260.13450.0497
    • Table 2. Recognition rate and matching time (HKPU-FKP noise database)

      View table

      Table 2. Recognition rate and matching time (HKPU-FKP noise database)

      AlgorithmGabor+LDAPCAHaarLBPSurfaceletTetrolet2DPCANTES
      WCRR/%94.270593.216795.761292.807593.495594.265896.285197.7328
      Matching time/s0.15290.10240.07680.02750.17620.11210.16720.0526
    • Table 3. Equal error rate and matching time (HKPU-FKP database)

      View table

      Table 3. Equal error rate and matching time (HKPU-FKP database)

      AlgorithmLGIC[19]LBPPCALGIC2[20]2DPCANTES
      WEER/%0.4023.50464.25910.3583.47052.5646
      Matching time/s0.26180.01260.0987<0.50000.13450.0497
    • Table 4. Recognition rate and matching time (IIT Delhi-FK original database)

      View table

      Table 4. Recognition rate and matching time (IIT Delhi-FK original database)

      AlgorithmGabor+LDAPCAHaarLBPSurfaceletTetrolet2DPCANTES
      WCRR/%96.952394.032395.265894.569695.658696.963397.025698.0158
      Matching time/s0.15230.08450.0600.02450.11450.12950.15620.0552
    • Table 5. Recognition rate and matching time (IIT Delhi-FK noise database)

      View table

      Table 5. Recognition rate and matching time (IIT Delhi-FK noise database)

      AlgorithmGabor+LDAPCAHaarLBPSurfaceletTetrolet2DPCANTES
      WCRR/%94.375293.508794.757893.250693.312195.158295.316497.1328
      Matching time/s0.17230.10810.08320.05760.13210.13080.16420.0672
    • Table 6. Recognition rate and matching time(HKPU-CFK original database)

      View table

      Table 6. Recognition rate and matching time(HKPU-CFK original database)

      AlgorithmGabor+LDAPCAHaarLBPSurfaceletTetrolet2DPCANTES
      WCRR/%97.235693.251796.179893.507494.895196.213597.332198.0027
      Matching time/s0.19250.11250.07230.01850.17230.08270.17280.0572
    • Table 7. Recognition rate and matching time(HKPU-CFK noise database)

      View table

      Table 7. Recognition rate and matching time(HKPU-CFK noise database)

      AlgorithmGabor+LDAPCAHaarLBPSurfaceletTetrolet2DPCANTES
      WCRR/%95.952592.573295.851291.565393.705895.367596.270897.1631
      Matching time/s0.20320.13240.09080.03260.18720.10340.19070.0625
    Tools

    Get Citation

    Copy Citation Text

    Yuan Wang, Sen Lin. Finger-Knuckle-Print Recognition Based on NSST and Tetrolet Energy Features[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0210019

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Jun. 17, 2020

    Accepted: Jul. 20, 2020

    Published Online: Jan. 11, 2021

    The Author Email: Wang Yuan (826998554@qq.com)

    DOI:10.3788/LOP202158.0210019

    Topics