Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

An Open Source Iris Segmentation Algorithm for Non-ideal Images

Published

Author(s)

George W. Quinn

Abstract

This document describes a new approach to localizing the iris boundaries in non-ideal iris images. The proposed algorithm starts by applying a series of morphological operations to enhance the salience of the iris boundaries while mitigating the impact of noise. A circular hough transform is then used to detect the pupil boundary. Finally, the fit is optimized via a gradient ascent algorithm that maximizes an objective reward function that quantifies the curve's goodness-of-fit. The efficacy of the proposed algorithm is demonstrated over two datasets, Notre Dame 0405 and the OPS 4 iris dataset used for principle performance testing in the IREX 10 ongoing evaluation. For the first dataset, the algorithm was able to correctly localize the boundaries in 831 out of 837 images, or 99.3% of the time, making it competitive with other open source algorithms. For the second, the algorithm was able to correctly localize the boundaries 99.2% of the time. The algorithm's source code is free for developers and universities to download and use.
Citation
NIST Interagency/Internal Report (NISTIR) - 8516
Report Number
8516

Keywords

biometrics, iris recognition, extreme value theory, Gumbel distribution, Hamming Dis- tance.

Citation

Quinn, G. (2024), An Open Source Iris Segmentation Algorithm for Non-ideal Images, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=935825 (Accessed October 15, 2024)

Issues

If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.

Created March 7, 2024