Combination of physiological and behavioral biometric for human identification

  • Authors:
  • Emdad Hossain;Girija Chetty

  • Affiliations:
  • Faculty of Information Sciences and Engineering, University of Canberra, Australia;Faculty of Information Sciences and Engineering, University of Canberra, Australia

  • Venue:
  • MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we propose a novel person-identification scheme based on gait biometric information in surveillance videos using simple PCA-LDA features, and RBF-MLP and SMO-SVM classifier. The experimental evaluation on resolution surveillance video images from a publicly available database [1] showed that the combined PCA-MLP and LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns.