Personal identification using knuckleprint

  • Authors:
  • Qiang Li;Zhengding Qiu;Dongmei Sun;Jie Wu

  • Affiliations:
  • Institute of Information Science, Beijing Jiaotong University, Beijing, P.R China;Institute of Information Science, Beijing Jiaotong University, Beijing, P.R China;Institute of Information Science, Beijing Jiaotong University, Beijing, P.R China;Institute of Information Science, Beijing Jiaotong University, Beijing, P.R China

  • Venue:
  • SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

A novel biometric defined as “knuckleprint” is presented in this paper The Line feature of the knuckleprint with its distribution in the finger (which is defined as location feature) is extracted to identify a person To enhance the performance of identification, hierarchical classification method is used to classify the location feature and line feature in different levels Though this is the first attempt of knuckleprint identification, the accuracy rate reaches 96.88% on the database that contains 1,432 image samples, which testifies that knuckleprint is reliable as a biometric, and demonstrates the effectiveness and robustness of the features.