By Topic

Partial iris image recognition using wavelet based texture features

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Md. Rabiul Islam ; Faculty of Computer Science and Information Technology, Universiti Malaysia Sarawak, 94300, Kota Samarahan, Malaysia ; Yin Chai Wang ; Asma Khatun

Now a day's security is the key issue all over in the world and iris biometric is shown to be the most authentic and accurate for human identification. In this paper, an effective partial iris image recognition is described based on wavelet texture features where capturing the entire iris may not be feasible. Daubechies 4-level Db8 wavelet transform is applied to two small portions namely left and right sub-images of the irises to extract distinctive iris features which is comprised of only 510 bits whereas existing approaches extracted as many as 1024 bits to represent the unique feature vector. Hamming distance similarity measurement technique was employed for recognition. The experimental results show that it is possible to use only significant portion (left and right sub-image) of the irises for human identification.

Published in:

Intelligent and Advanced Systems (ICIAS), 2010 International Conference on

Date of Conference:

15-17 June 2010