Advertisement

A Novel Segmentation Algorithm of Fingerprint Images Based on Mean Shift

  • Zhe Xue
  • Tong Zhao
  • Min Wu
  • Tiande Guo
Part of the Communications in Computer and Information Science book series (CCIS, volume 304)

Abstract

The segmentation of fingerprint images is an important step in an automatic fingerprint identification system (AFIS). It is used to identify the foreground of a fingerprint image. Existing methods are usually based on some point features such as average gray level, variance, Gabor response, etc, while they ignored the local information of foreground regions. In this paper, a novel segmentation approach is proposed based on the mean shift algorithm, which not only take advantage of the traditional features, but also use the local information. In order to segment the fingerprint image better, we modified the original mean shift segmentation algorithm. First we calculate some effective features of fingerprint images and determine the parameters adaptively, and then we process the image based on the mean shift algorithm and get some divided regions, finally the foreground are selected from these regions. The accuracy and effectiveness of our method are validated by experiments performed on FVC database.

Keywords

mean shift fingerprint image segmentation image processing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mehtre, B.M., Murthy, N.N., Kapoor, S., Chatterjee, B.: Segmentation of Fingerprint Images Using Directional Image. Pattern Recognition 20(4), 429–435 (1987)CrossRefGoogle Scholar
  2. 2.
    Ratha, N.K., Chen, S., Jain, A.K.: Adaptive Flow Orientation-Based Feature Extraction in Fingerprint Images. Pattern Recognition 28(11), 1657–1672 (1995)CrossRefGoogle Scholar
  3. 3.
    Shen, L., Kot, A.C., Koo, W.M.: Quality Measures of Fingerprint Images. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 266–271. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  4. 4.
    Fernando, A.F., Julian, F.A., Javier, O.G.: An Enhanced Gabor Filter-Based Segmentation Algorithm for Fingerprint Recognition Systems. In: Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, pp. 239–244 (2005)Google Scholar
  5. 5.
    Asker, M., Bazen, S.H.: Gerez: Segmentation of Fingerprint Images. In: ProRISC 2001 Workshop on Circuits, Systems and Signal Processing, Veldhoven, The Netherlands (2001)Google Scholar
  6. 6.
    Liu, E., Zhao, H., Guo, F.F., Liang, J.M., Tian, J.: Fingerprint segmentation based on an AdaBoost classifier. Frontiers of Computer Science in China 5(2), 148–157Google Scholar
  7. 7.
    Fukunaga, K., Hostetler, L.D.: The Estimation of the Gradient of a Density Functions with Applications in Pattern Recognition. IEEE Trans. on Information Theory 21(1), 32–40 (1975)MathSciNetzbMATHCrossRefGoogle Scholar
  8. 8.
    Cheng, Y.Z.: Mean Shift, mode seeking, and clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence 17(8), 790–799 (1995)CrossRefGoogle Scholar
  9. 9.
    Comaniciu, D., Meer, P.: Robust Analysis of Feature Spaces: Color Image Segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 1997), San Juan, PR, USA, pp. 750–755 (1997)Google Scholar
  10. 10.
    Comaniciu, D., Meer, P.: Mean Shift: A Robust Approach toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(5), 603–619 (2002)CrossRefGoogle Scholar
  11. 11.
  12. 12.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zhe Xue
    • 1
  • Tong Zhao
    • 2
  • Min Wu
    • 1
  • Tiande Guo
    • 2
  1. 1.School of information Sciences and EngineeringGraduate University of Chinese, Academy of SciencesBeijingChina
  2. 2.School of mathematical SciencesGraduate University of Chinese Academy, of SciencesBeijingChina

Personalised recommendations