Back to search

West Virginia University

Enhanced iris recognition: Algorithms for segmentation, matching and synthesis

Abstract

dc:description.abstract

This thesis addresses the issues of segmentation, matching, fusion and synthesis in the context of irises and makes a four-fold contribution. The first contribution of this thesis is a post matching algorithm that observes the structure of the differences in feature templates to enhance recognition accuracy. The significance of the scheme is its robustness to inaccuracies in the iris segmentation process. Experimental results on the CASIA database indicate the efficacy of the proposed technique. The second contribution of this thesis is a novel iris segmentation scheme that employs Geodesic Active Contours to extract the iris from the surrounding structures. The proposed scheme elicits the iris texture in an iterative fashion depending upon both the local and global conditions of the image. The performance of an iris recognition algorithm on both the WVU non-ideal and CASIA iris database is observed to improve upon application of the proposed segmentation algorithm. The third contribution of this thesis is the fusion of multiple instances of the same iris and multiple iris units of the eye, i.e., the left and right iris at the match score level. Using simple sum rule, it is demonstrated that both multi-instance and multi-unit fusion of iris can lead to a significant improvement in matching accuracy. The final contribution is a technique to create a large database of digital renditions of iris images that can be used to evaluate the performance of iris recognition algorithms. This scheme is implemented in two stages. In the first stage, a Markov Random Field model is used to generate a background texture representing the global iris appearance. In the next stage a variety of iris features, viz., radial and concentric furrows, collarette and crypts, are generated and embedded in the texture field. Experimental results confirm the validity of the synthetic irises generated using this technique.

Degree

thesis:*
Name thesis:degree_name
MS
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Lane Department of Computer Science and Electrical Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Shah, Samir

Subjects

dc:subject × 1

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
West Virginia University
Base URL
researchrepository.wvu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Shah, Samir. Enhanced iris recognition: Algorithms for segmentation, matching and synthesis. Thesis thesis, https://doi.org/10.33915/etd.2481