Skip to content

Kozlowski-Bartosz/Iris-image-quality-assessment

Repository files navigation

Iris Image Quality Asssessment

Introduction

This repository contains the code for the thesis "Ocular image quality assessment for the purposes of iris recognition" by Bartosz Kozłowski, supervised by dr inż. Wojciech Wodo. The thesis was written at the Faculty of Information Technology and Telecomunication (W4N), Wroclaw University of Science and Technology.

The program is able to assess the quality of an iris image following the ten recommended metrics from the ISO/IEC 29794-6:2015 standard, which are:

  • Usable iris area
  • Iris-sclera contrast
  • Iris-pupil contrast
  • Pupil boundary circularity
  • Grey-scale utilization
  • Iris radius
  • Pupil dilation
  • Iris pupil concentricity
  • Margin adequacy
  • Sharpness

Instructions

The parameter files need to follow the naming convention of: <image_name_without_extension><params_suffix> (For example: 001_1_1_para.txt, where 001_1_1 is the image name, and _para.txt was configured as the parameter suffix in the config.ini file). Similarly, the mask files need to follow the naming convention of: <image_name_without_extension><mask_suffix> (For example: 001_1_1_mask.bmp). The mask files need to be binary images, where 1 represents the iris and 0 represents the background. The mask files need to be the same size (width and height) as the corresponding image.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages