Iterative Directional Ray Based Iris Segmentation for Challenging Periocular Images

Abstract

The face region immediately surrounding one, or both, eyes is called the periocular region. This paper presents an iris segmentation algorithm for challenging periocular images based on a novel iterative ray detection segmentation scheme. Our goal is to convey some of the difficulties in extracting the iris structure in images of the eye characterized by variations in illumination, eye-lid and eye-lash occlusion, de-focus blur, motion blur, and low resolution. Experiments on the Face and Ocular Challenge Series (FOCS) database from the U.S. National Institute of Standards and Technology (NIST) emphasize the pros and cons of the proposed segmentation algorithm.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 03, 2011
Accession Number
AD1040945

Entities

People

  • Robert Plemmons
  • V. Paul Pauca
  • Xiaofei Hu

Organizations

  • Wake Forest University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Boundaries
  • Calculus Of Variations
  • Computer Science
  • Computer Vision
  • Curve Fitting
  • Databases
  • Detection
  • Detectors
  • Directional
  • Identification
  • Illumination
  • Intellectual Property
  • Military Research
  • Recognition
  • Specular Reflection

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Toxicology/Environmental Toxicology
  • Wave Propagation and Nonlinear Chaotic Dynamics.