Segmentation-free Direct Iris Localization Networks

TL;DR

This paper introduces a fast, segmentation-free iris localization network that directly detects iris features from low-resolution images, outperforming traditional methods in speed, robustness, and accuracy.

Contribution

The paper presents a novel iris localization network (ILN) and pupil refinement network (PRN) that eliminate the need for segmentation and circle fitting, reducing computational costs and improving robustness.

Findings

Works in 34.5 ms per image on CPU

Outperforms conventional segmentation methods in accuracy

Demonstrates higher robustness across different datasets

Abstract

This paper proposes an efficient iris localization method without using iris segmentation and circle fitting. Conventional iris localization methods first extract iris regions by using semantic segmentation methods such as U-Net. Afterward, the inner and outer iris circles are localized using the traditional circle fitting algorithm. However, this approach requires high-resolution encoder-decoder networks for iris segmentation, so it causes computational costs to be high. In addition, traditional circle fitting tends to be sensitive to noise in input images and fitting parameters, causing the iris recognition performance to be poor. To solve these problems, we propose an iris localization network (ILN), that can directly localize pupil and iris circles with eyelid points from a low-resolution iris image. We also introduce a pupil refinement network (PRN) to improve the accuracy of pupil localization. Experimental results show that the combination of ILN and PRN works in 34.5 ms for one iris image on a CPU, and its localization performance outperforms conventional iris segmentation methods. In addition, generalized evaluation results show that the proposed method has higher robustness for datasets in different domain than other segmentation methods. Furthermore, we also confirm that the proposed ILN and PRN improve the iris recognition accuracy.