|
Title:
|
A NOVEL IRIS SEGMENTATION FRAMEWORK |
|
Author(s):
|
Ivan A. Matveev |
|
ISBN:
|
978-989-8533-22-7 |
|
Editors:
|
Katherine Blashki and Yingcai Xiao |
|
Year:
|
2014 |
|
Edition:
|
Single |
|
Keywords:
|
Image processing, iris segmentation. |
|
Type:
|
Full Paper |
|
First Page:
|
215 |
|
Last Page:
|
222 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
A framework of methods for iris location and segmentation in eye image is presented. The basic idea of the framework is that in the beginning stages the most general features should be detected and then gradually refined to evaluate more detailed object description in the ending stages. Each iris parameter is revised several times. System starts with approximate detection of eye center position followed by approximate simultaneous detection of inner and outer boundaries of iris region. If one of the boundaries is not detected, an additional attempt to locate it is performed with the help of alternative method. Finally precise borders are detected at last steps of processing by specially designed methods. The system capability is verified with public domain databases of iris images, as well as in international IREX NIST test. |
|
|
|
|
|
|
