ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Iris Recognition for Person Identification

Matic Likozar (2017) Iris Recognition for Person Identification. EngD thesis.

Download (14Mb)


    Biometrics is the process of collecting, studying and comparing the individual's physical characteristics in order to identify and authenticate. Biometric systems allow automated identification of an individual based on the unique pattern. Identification based on iris represents one of the most reliable systems for identifying individuals. Most commercial systems operate based on Daugman's method, which showed excellent results, both in the time complexity, as well as the rate of success when identifying persons. The aim of this work is to present the basic operation of the system for identifying the iris. The system comprises five main methods: image acquisition, iris segmentation, iris normalization, feature extraction and pattern matching. Details will be presented by each method of Daugman's system and compared with Wilde's system. Based on presented methods we will develop our own method for iris recognition.

    Item Type: Thesis (EngD thesis)
    Keywords: biometric identification, iris recognition, segmentation, normalization, iris pattern
    Number of Pages: 58
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    viš. pred. dr. Borut Batagelj298Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537410755)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3848
    Date Deposited: 31 Mar 2017 14:04
    Last Modified: 19 Apr 2017 11:47
    URI: http://eprints.fri.uni-lj.si/id/eprint/3848

    Actions (login required)

    View Item