Iris Image Processing in Compressive Sensing Scenario

TL;DR

This paper explores the use of Compressive Sensing techniques for reconstructing under-sampled iris images to improve biometric identification, comparing different sparsity domains and validating the approach on real iris data.

Contribution

It introduces a novel application of Compressive Sensing to iris image reconstruction, analyzing various sparsity domains and their effectiveness in biometric recognition.

Findings

Compressive Sensing can effectively reconstruct iris images from limited data.

Different sparsity domains impact reconstruction quality.

The approach is validated on real iris images.

Abstract

This paper observes the application of the Compressive Sensing in reconstruction of the under-sampled iris images. Iris recognition represents form of biometric identification whose usage in real applications is growing. Compressive Sensing represents a novel form of sparse signal acquisition and recovering when small amount of data is a available. Different sparsity domains are considered and compared using various number of available image pixels. The theory is verified on iris images.