Journal of Beijing University of Posts and Telecommunications

  • EI核心期刊

JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM ›› 2006, Vol. 29 ›› Issue (2): 38-41.doi: 10.13190/jbupt.200602.38.zhaoyy

• Papers • Previous Articles     Next Articles

Fingerprint Image Segmentation Based on Support Vector Machines

ZHAO Yan-yun, CAI An-ni   

  1. School of Telecommunication Engineering, Beijing University of Posts and Telecommunications
  • Online:2006-04-28 Published:2006-04-28

Abstract: We present a fingerprint image segmentation algorithm based on support vector machines(SVM). The algorithm uses the features of the gray variance and contrast to train the SVM for image segmentation, and fits the segmentation result of the SVM to convex hull. The experimental results show the algorithm is robust, especially for training segmentation algorithm with a small quantity of samples.

Key words: image segmentation, support vector machines, convex hull