An Effective Method for Eyelashes Segmentation Using Wavelet Transform

Author

Aligholizadeh, M.J. ; Javadi, S. ; Sabbaghi-nadooshan, Reza ; Kangarloo, Kaveh

Author_Institution

Sci. Assoc. of Electr. & Electron. Eng., Islamic Azad Univ. Central, Tehran, Iran

fYear

2011

fDate

19-22 Sept. 2011

Firstpage

185

Lastpage

188

Abstract

In an iris recognition system, iris segmentation is an important step. Some regions of iris are occluded by eyelashes so the eyelashes reduce the performance of iris recognition system. In this paper, we present an effective method for eyelashes segmentation. In the first step, eyelashes are detected using the wavelet transform. As regards, the eyelashes are similar to lines in the eye images so in the second step, we use the Hough transform for eyelashes modeling. In the last step, the eyelashes are segmented using the neural network. In this paper we use the CASIA version 1.0 database. The experimental results show the satisfactory performance.

Keywords

Hough transforms; eye; image segmentation; iris recognition; neural nets; wavelet transforms; CASIA version 1.0 database; Hough transform; eyelash modeling; eyelash segmentation; iris recognition system; iris segmentation; neural network; wavelet transform; Eyelashes; Image edge detection; Image segmentation; Iris recognition; Wavelet transforms; Hough transform; Iris segmentation; eyelash; neural network; pupil; wavelet transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Biometrics and Kansei Engineering (ICBAKE), 2011 International Conference on

Conference_Location

Takamatsu, Kagawa

Print_ISBN

978-1-4577-1356-9

Electronic_ISBN

978-0-7695-4512-7

Type

conf

DOI

10.1109/ICBAKE.2011.46

Filename

6031275