Iris-SAM: Iris Segmentation Using a Foundation Model

TL;DR

This paper presents Iris-SAM, a novel iris segmentation model that fine-tunes a foundation model with specialized loss functions, achieving high accuracy in iris segmentation tasks across multiple datasets.

Contribution

It introduces a fine-tuning approach of the Segment Anything Model with Focal Loss for improved iris segmentation performance.

Findings

Achieved 99.58% accuracy on ND-IRIS-0405 dataset.

Outperformed baseline methods with 89.75% accuracy.

Validated effectiveness across three iris datasets.

Abstract

Iris segmentation is a critical component of an iris biometric system and it involves extracting the annular iris region from an ocular image. In this work, we develop a pixel-level iris segmentation model from a foundational model, viz., Segment Anything Model (SAM), that has been successfully used for segmenting arbitrary objects. The primary contribution of this work lies in the integration of different loss functions during the fine-tuning of SAM on ocular images. In particular, the importance of Focal Loss is borne out in the fine-tuning process since it strategically addresses the class imbalance problem (i.e., iris versus non-iris pixels). Experiments on ND-IRIS-0405, CASIA-Iris-Interval-v3, and IIT-Delhi-Iris datasets convey the efficacy of the trained model for the task of iris segmentation. For instance, on the ND-IRIS-0405 dataset, an average segmentation accuracy of 99.58% was achieved, compared to the best baseline performance of 89.75%.