Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment

TL;DR

This paper introduces Iris R-CNN, a deep learning framework that significantly improves iris segmentation accuracy in non-cooperative environments by leveraging novel network components and normalization techniques.

Contribution

The paper presents a novel deep learning framework with specialized networks and normalization schemes tailored for accurate iris segmentation in challenging conditions.

Findings

Outperforms state-of-the-art methods on UBIRIS.v2 and MICHE datasets.

Achieves superior segmentation accuracy in non-cooperative environments.

Introduces double-circle region proposal and normalization techniques.

Abstract

Despite the significant advances in iris segmentation, accomplishing accurate iris segmentation in non-cooperative environment remains a grand challenge. In this paper, we present a deep learning framework, referred to as Iris R-CNN, to offer superior accuracy for iris segmentation. The proposed framework is derived from Mask R-CNN, and several novel techniques are proposed to carefully explore the unique characteristics of iris. First, we propose two novel networks: (i) Double-Circle Region Proposal Network (DC-RPN), and (ii) Double-Circle Classification and Regression Network (DC-CRN) to take into account the iris and pupil circles to maximize the accuracy for iris segmentation. Second, we propose a novel normalization scheme for Regions of Interest (RoIs) to facilitate a radically new pooling operation over a double-circle region. Experimental results on two challenging iris databases, UBIRIS.v2 and MICHE, demonstrate the superior accuracy of the proposed approach over other state-of-the-art methods.