An Accurate Iris Segmentation Framework under Relaxed Imaging Constraints using Total Variation Model

Iris recognition is one of the most accurate and widely employed approaches for the automated personal identification. In this work we develop a new and more accurate iris segmentation framework to automatically segment iris region from the face images acquired with relaxed imaging under visible or near-infrared illumination, which provides strong feasibility for applications in surveillance, forensics and the search for missing children, etc. The proposed framework is built on a novel total-variation based formulation which uses l1 norm regularization to robustly suppress noisy texture pixels for the accurate iris localization. The intermediate results from two automatically detected eye samples are  reproduced in the following figure.

Intermediate Results for Iris Segmentation

A series of novel and robust post processing operations are introduced to more accurately localize the limbic boundaries. Our experimental results on three publicly available databases, i.e., FRGC, UBIRIS.v2 and CASIA.v4-distance, achieve significant performance improvement in terms of iris segmentation accuracy over the state-of-the-art approaches in the literature. Besides, we have shown that using iris masks generated from the proposed approach helps to improve iris recognition performance as well. Unlike prior work, all the implementations in this paper are made publicly available to further advance research and applications in biometrics at-d-distance..

Implementation Codes for At-A-Distance Iris Segmentation Algorithm

You can download the implementation codes used to develop and evaluate the algorithm described in this paper.  The details and the link for the files appear in the following. The codes are in Matlab and provides all the parameters required to reproduce the results.

ReadMe File

A readme.txt file provides details on running the programs on each of the three distantly acquired iris/eye images databases employed in this work. 

Download and Copyright

The implementation codes are made available for the researchers from December 2015 onwards. Interested researchers should downlload the file and follow the steps detailed in the readme file. This implementation or software is provided on 'as it is' basis and does not include any warranty of any kind.




[1] Zijing Zhao, Ajay Kumar   An Accurate Iris Segmentation Framework under Relaxed Imaging Constraints using Total Variation Model”,  Proc. ICCV 2015, pp. 3828-3836, Santiago, Chile, Dec. 2015.