Palm veins recognition and verification system

Other Title(s)

منظومة للتمييز و التحقيق من أوردة راحة اليد

Dissertant

Abbas, Asma Muhammad Jawad

Thesis advisor

Jurj, Luayy Adwar

Comitee Members

Dhannun, Ban Nadim
al-Abbudi, Bushra Qasim
Muhammad, Faysal Ghazi

University

University of Baghdad

Faculty

College of Science

Department

Department of Computer Science

University Country

Iraq

Degree

Master

Degree Date

2014

English Abstract

During the last years, hand vein patterns recognition is one of the most recent biometric technologies used for the identification/verification of individuals.

The vein trace is hard to damaged, changed or falsified since veins are internal to the human body.

In this work, a novel palm vein recognition and verification system is presented.

The system work flow passes through two main phases: (i) the enrollment phase and (ii) the recognition phase.

In the enrollment phase, the biometric system is trained to identity a specific person.

While, in the recognition phase, the system tries to identify who is the person (in case of identification) or to verify is the person who he/she claims to be (in case of verification).

The imaging quality and variability of the vein images acquired by the near-infrared (NIR) device present challenges to achieve high classification accuracy.

In the proposed system, the first two steps are image preprocessing and, then, the localization of veins grid (i.e., the region of interest, ROI).

So, the infrared palm image is entered into the preprocessing stage to improve the appearance of veins by applying a set of enhancement process, then, segmentation process is applied to isolate the veins grid area; a post-processing operation is, also applied to improve the shape of veins grid.

The palm vein feature extraction task is another challenging problem in the infrared hand palm recognition tasks.

In this research two set of features have been suggested to represent the veins grid attributes: (i) the spatial distribution of the local average of veins direction and (ii) the spatial energy distribution of wavelet sub-bands.

Each extracted feature list is assembled as a feature vector used to distinguish between palms belonging to different persons.

Euclidean Distance and City Block Distance measures have been used to make a decision in matching stage.

The system was tested over a database collected from 250 volunteers, where 24 images for the 2 palms of each person were collected.

In total, the database contains 6,000 images belonging to 500 different palms.

The achieved identification results indicated a high recognition rate of 99.95% when using the spatial distribution of the average of veins direction, and an excellent recognition rate of 100% when using spatial energy distribution of wavelet sub-bands.

The verification experimental results referred to a minimum error rate (equal error rate (EER)) equals 0.24%when using the first feature set; and equals 0.068% when using the second set.

These results indicate that the proposed method is perfect for palm-vein recognition tasks.

Main Subjects

Information Technology and Computer Science

Topics

• Blood-vessels
• Data processing

No. of Pages

101

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-605925