Multi-biometrics 2d and 3d ear recognition

  • Authors:
  • Ping Yan;Kevin W. Bowyer

  • Affiliations:
  • Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN;Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN

  • Venue:
  • AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Multi-biometric 2D and 3D ear recognition are explored. The data set used represents over 300 persons, each with images acquired on at least two different dates. Among them, 169 persons have images taken on at least four different dates. Based on the results of three algorithms applied on 2D and 3D ear data, various multi-biometric combinations were considered, and all result in improvement over a single biometric. A new fusion rule using the interval distribution between rank 1 and rank 2 outperforms other simple fusion rules. In general, all the approaches perform better with multiple representations of a person.