Fingerprint matching based on weighting method and the SVM

  • Authors:
  • Jia Jia;Lianhong Cai;Pinyan Lu;Xuhui Liu

  • Affiliations:
  • Key Laboratory of Pervasive Computing, Tsinghua University, Ministry of Education, Beijing 100084, PR China;Key Laboratory of Pervasive Computing, Tsinghua University, Ministry of Education, Beijing 100084, PR China;Key Laboratory of Pervasive Computing, Tsinghua University, Ministry of Education, Beijing 100084, PR China;Key Laboratory of Pervasive Computing, Tsinghua University, Ministry of Education, Beijing 100084, PR China

  • Venue:
  • Neurocomputing
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

Fingerprint verification is an important biometric technology. In this paper, an improved fingerprint matching approach that uses both the weighting method and the support vector machine (SVM) is presented. A new weighting feature based on the distance between minutiae is introduced to supplement the minutiae information, which is particularly useful for fingerprint images of poor quality. Furthermore, the traditional minutiae-based matching task is studied as a classification task in the proposed approach by using SVM. To give an objective assessment of the approach, both international and domestic fingerprint verification competition databases have been used for the evaluation. Experimental results show substantial improvements in the accuracy and performance of fingerprint verification.