Information distance-based selective feature clarity measure for iris recognition

Craig Belcher; Yingzi Du

doi:10.1117/12.704702

29 January 2007 Information distance-based selective feature clarity measure for iris recognition

Craig Belcher, Yingzi Du

Proceedings Volume 6494, Image Quality and System Performance IV; 64940E (2007) https://doi.org/10.1117/12.704702
Event: Electronic Imaging 2007, 2007, San Jose, CA, United States

Abstract

Iris recognition systems have been tested to be the most accurate biometrics systems. However, poor quality images greatly affect accuracy of iris recognition systems. Many factors can affect the quality of an iris image, such as blurriness, resolution, image contrast, iris occlusion, and iris deformation, but blurriness is one of the most significant problems for iris image acquisition. In this paper, we propose a new method to measure the blurriness of an iris image called information distance based selective feature clarity measure. Different from any other approach, the proposed method automatically selects portions of the iris with most changing patterns to measure the level of blurriness based on their frequency characteristics. Log-Gabor wavelet is used to capture the features of the selected portions. By comparing the information loss from the original features to blurred versions of the same features, the algorithm decides the clarity of the original iris image. The preliminary experiment results show that this method is effective.

Citation Download Citation

Craig Belcher and Yingzi Du "Information distance-based selective feature clarity measure for iris recognition", Proc. SPIE 6494, Image Quality and System Performance IV, 64940E (29 January 2007); https://doi.org/10.1117/12.704702

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available