Pith. sign in

REVIEW 1 cited by

Iris-SAM: Iris Segmentation Using a Foundation Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.06497 v3 pith:FPZRWOGA submitted 2024-02-09 cs.CV

classification cs.CV
keywords irismodelsegmentationfine-tuninglossnd-iris-0405ocularwork
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Can Foundation Models Generalise the Presentation Attack Detection Capabilities on ID Cards?

    cs.CV 2025-06 reject novelty 4.0 of 10

    DinoV2 features improve ID card presentation attack detection under leave-one-out protocols, and the paper argues that representative bona fide images, not attack diversity, are what enable generalization.

Pith tools