Robust iris verification for key management

  • Authors:
  • Sheikh Ziauddin;Matthew N. Dailey

  • Affiliations:
  • Computer Science and Information Management, Asian Institute of Technology, P.O. Box 4, Klong Luang, Pathumthani 12120, Thailand;Computer Science and Information Management, Asian Institute of Technology, P.O. Box 4, Klong Luang, Pathumthani 12120, Thailand

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2010

Quantified Score

Hi-index 0.11

Visualization

Abstract

In this paper, we present a method for secret key generation and recovery based on iris verification that, unlike typical systems which store iris templates persistently, stores recovery information on a smart card carried by the user. The scheme uses error-correcting codes to overcome the noisiness inherent in biometric readings. Our iris template incorporates reliable region selection, reliable bit estimation and one-sided masking techniques that provide for both robust verification and large key sizes. An implementation and experiments with the University of Bath iris dataset indicate that our scheme provides for generation and recovery of 260-bit keys with an EER of 0%.