A two stage neural network-based personal identification system using handprint

  • Authors:
  • Jun Kong;Yinghua Lu;Shuhua Wang;Miao Qi;Hongzhi Li

  • Affiliations:
  • Computer School, Northeast Normal University, Changchun, Jilin, China and Key Laboratory for Applied Statistics of MOE, China;Computer School, Northeast Normal University, Changchun, Jilin, China;Computer School, Northeast Normal University, Changchun, Jilin, China and Key Laboratory for Applied Statistics of MOE, China;Computer School, Northeast Normal University, Changchun, Jilin, China and Key Laboratory for Applied Statistics of MOE, China;Computer School, Northeast Normal University, Changchun, Jilin, China and Key Laboratory for Applied Statistics of MOE, China

  • Venue:
  • Neurocomputing
  • Year:
  • 2008

Quantified Score

Hi-index 0.01

Visualization

Abstract

With the increasing emphasis on security, automated personal identification based on biometrics has been receiving extensive attention over the past decades. Handprint identification, as an emerging biometric identification technology, is receiving more and more attention in both research and practical applications as time goes by. In this paper, a novel approach for handprint identification is proposed. Firstly, region of interest is segmented through hand's key points localization, then the Gabor filtering and Zernike moments methods are used to extract the palmprint features. A two stage neural network structure is employed to measure the degree of similarity in the identification stage. The experimental results demonstrate that the proposed approach is effective and feasible.