Human Vein Pattern Correlation - A Comparison of Segmentation Methods

  • Rafał Kabaciński
  • Mateusz Kowalski
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 95)

Abstract

In this paper two methods of human vein pattern segmentation from low quality images, called frequency high-pass filtration and local minima analysis, proposed by authors in their previous article are compared with the often used local thresholding algorithm. These methods are evaluated using results of classification performed by a correlation algorithm. Evaluation was carried out on 400 collected images, and shows that proposed methods are worth to consider in human vein pattern segmentation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anil, K.J., Flynn, P.J., Ross, A.A.: Handbook of biometrics. Springer, Berlin (2008)Google Scholar
  2. 2.
    Crisan, S., Tarnovan, I.G., Crisan, T.E.: Vein pattern recognition. Image enhancement and feature extraction algorithms. In: 15th Symposium on Novelties in Electrical Measurements and Instrumentation in parallel with the 12th Workshop on ADC Modelling and Testing, Iasi (2007)Google Scholar
  3. 3.
    Lam, L., Lee, S.-W., Suen Ch, Y.: IEEE Transactions on Pattern Analysis And Machine Inteligence 14, 869–885 (1992)CrossRefGoogle Scholar
  4. 4.
    Kabaciński, R., Kowalski, M.: Advances in Soft Computing 84, 105–112 (2010)CrossRefGoogle Scholar
  5. 5.
    Shahin, M., Badawi, A., Kamel, M.: International Journal of Biological and Life Sciences 2, 141–148 (2006)Google Scholar
  6. 6.
    Wang, L., Leedham, G., Cho, D.S.-Y.: Pattern Recognition 41, 920–929 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Rafał Kabaciński
    • 1
  • Mateusz Kowalski
    • 1
  1. 1.Institute of Control and Information EngineeringPoznan University of TechnologyPoznańPoland

Personalised recommendations