Feature extraction using two dimensional (2D) legendre wavelet filter for partial iris recognition

Muktar, Danlami (2020) Feature extraction using two dimensional (2D) legendre wavelet filter for partial iris recognition. Doctoral thesis, Universiti Tun Hussein Onn Malaysia.


Download (4MB) | Preview
[img] Text (Copyright Declaration)
Restricted to Repository staff only

Download (4MB) | Request a copy
[img] Text (Full Text)
Restricted to Registered users only

Download (5MB) | Request a copy


An increasing need for biometrics recognition systems has grown substantially to address the issues of recognition and identification, especially in highly dense areas such as airports, train stations, and financial transactions. Evidence of these can be seen in some airports and also the implementation of these technologies in our mobile phones. Among the most popular biometric technologies include facial, fingerprints, and iris recognition. The iris recognition is considered by many researchers to be the most accurate and reliable form of biometric recognition because iris can neither be surgically operated with a chance of losing slight nor change due to aging. However, presently most iris recognition systems available can only recognize iris image with frontal-looking and high-quality images. Angular image and partially capture image cannot be authenticated with the existing method of iris recognition. This research investigates the possibility of developing a technique for recognition partially captured iris image. The technique is designed to process the iris image at 50%, 25%, 16.5%, and 12.5% and to find a threshold for a minimum amount of iris region required to authenticate the individual. The research also developed and implemented two Dimensional (2D) Legendre wavelet filter for the iris feature extraction. The Legendre wavelet filter is to enhance the feature extraction technique. Selected iris images from CASIA, UBIRIS, and MMU database were used to test the accuracy of the introduced technique. The technique was able to produce recognition accuracy between 70 – 90% CASIA-interval with 92.25% accuracy, CASIA-distance with 86.25%, UBIRIS with 74.95%, and MMU with 94.45%.

Item Type: Thesis (Doctoral)
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions: Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User: Mrs. Sabarina Che Mat
Date Deposited: 06 Sep 2021 08:19
Last Modified: 06 Sep 2021 08:19
URI: http://eprints.uthm.edu.my/id/eprint/887

Actions (login required)

View Item View Item