ETRO VUB
About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Fast eye image processing and iris segmentation

Subject

Preprocessing of eye images and iris segmentation are the key components for applications of iris recognition and gaze tracking. Despite existing methods based on deep learning reach a high accuracy, they are computationally complex and require more processing power than some of the existing hand crafted methods. The popularity of mobile devices and their limited computational resources are amongst the causes of limited penetration of the technology in the end-user applications.
This work aims at developing an eye preprocessing method that performs real-time segmentation of an iris in a live camera stream on mobile devices. The student will explore the possibility of integration of a machine learning approach with hand crafted methods in order to improve efficiency and accuracy. The goal is to develop a method that has the potential to run on a mobile device utilizing various different computational resources (e.g. DSP, GPU)
Finally, the developed method is evaluated on different publicly available datasets of human iris (e.g. CASIA) and demonstrated on different devices available within the department - i.e. the student will develop an application running on a mobile device.

Relevant literature:
Z. He, T. Tan, and Z. Sun, "Iris localization via pulling and pushing," in Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, vol. 4, 0-0 2006, pp. 366-369.
H. Li, Z. Sun, and T. Tan. Robust iris segmentation based on learned boundary detectors. In ICB, 2012.

Kind of work

The thesis will consist of the following steps:
(1) Review of related literature
(2) Implementation of selected existing iris segmentation method
(3) Proposing a new method to improve over the state-of-the-art algorithms
(4) Writing the thesis

Framework of the Thesis

The thesis will be matched with the ongoing research themes at VUB-ETRO. The research results are expected to be published in an international conference.

Number of Students

1

Expected Student Profile

- Good programming skills in C/C++/Python
- Good knowledge of machine learning

Promotor

Prof. Dr. Bart Jansen

+32 (0)2 629 1034

bjansen@etrovub.be

more info

Supervisor

Mr. Lubos Omelina

+32 (0)2 629 1035

lomelina@etrovub.be

more info

Image

- Contact person

- IRIS

- AVSP

- LAMI

- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press

Contact

ETRO Department

info@etro.vub.ac.be

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer