Very Low-Resolution Iris Recognition Via Eigen-Patch Super-Resolution and Matcher Fusion

TL;DR

This paper introduces a super-resolution method based on Eigen-patch reconstruction and matcher fusion to improve low-resolution iris recognition, achieving significantly better accuracy than traditional interpolation methods.

Contribution

It presents a novel Eigen-patch super-resolution technique combined with matcher fusion, enhancing iris recognition performance at very low resolutions.

Findings

Super-resolution outperforms bilinear and bicubic interpolation at low resolutions.

Matcher fusion reduces EER below 5% for images as small as 13x13 pixels.

The approach is validated on a large near-infrared iris database.

Abstract

Current research in iris recognition is moving towards enabling more relaxed acquisition conditions. This has effects on the quality of acquired images, with low resolution being a predominant issue. Here, we evaluate a super-resolution algorithm used to reconstruct iris images based on Eigen-transformation of local image patches. Each patch is reconstructed separately, allowing better quality of enhanced images by preserving local information. Contrast enhancement is used to improve the reconstruction quality, while matcher fusion has been adopted to improve iris recognition performance. We validate the system using a database of 1,872 near-infrared iris images. The presented approach is superior to bilinear or bicubic interpolation, especially at lower resolutions, and the fusion of the two systems pushes the EER to below 5% for down-sampling factors up to a image size of only 13x13.