A study on iris image restoration

  • Authors:
  • Byung Jun Kang;Kang Ryoung Park

  • Affiliations:
  • Dept. of Computer Science, Biometrics Engineering Research Center, Sangmyung University, Seoul, Republic of Korea;Division of Media Technology, Biometrics Engineering Research Center, Sangmyung University, Seoul, Republic of Korea

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

Quantified Score

Hi-index 0.01

Visualization

Abstract

Because iris recognition uses the unique patterns of the human iris, it is essential to acquire the iris images at high quality for accurate recognition. Defocusing reduces the quality of the iris image and the performance of iris recognition, consequently. In order to acquire a focused iris image at high quality, an iris recognition camera must control the focal length of the moving lens. However, that causes the cost and size of iris camera to be increased and that needs complicated auto-focusing algorithm, also. To overcome such problems, we propose new method of iris image restoration. Experimental results show that the total recognition time is reduced as much as 390ms on average with the proposed restoration algorithm.