Biometric Security Application for Person Authentication Using Retinal Vessel Feature

A. Hussain, A. Bhuiyan, Ajmal Mian, K. Ramamohanarao

    Research output: Chapter in Book/Conference paperConference paper

    9 Citations (Scopus)

    Abstract

    Retinal vascular branch and crossover points are unique features for each individual that can be used as a reliable biometric for personal authentication and can be used for information retrieval and security application. In this work, a novel biometric authentication scheme is proposed based on the retinal vascular network features. We apply an automatic technique to detect and identify retinal vascular branch and crossover points. These branch and crossover points are mapped from prominent blood vessels in the image. For this, a novel vessel width measurement method is applied and vessels more than certain widths are selected. Based on these vessel segments their corresponding branch and crossover points are identified. Invariant features are constructed through Geometric Hashing of the detected branch and crossover points. We consider the crossover points for modelling a basis pair and all other points together for locations in the hash table entries. Thus, the models are invariant to rotation, translation and scaling. For each person, the system is trained with the models to accept or reject a claimed identity. The initial results show that the proposed method has achieved 100% detection accuracy which is highly potential for reliable person identification.
    Original languageEnglish
    Title of host publication2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages306-313
    ISBN (Print)9781479921263
    DOIs
    Publication statusPublished - 2013
    Event2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA) - Hobart, TAS, Hobart, Australia
    Duration: 26 Nov 201328 Nov 2013

    Conference

    Conference2013 International Conference on Digital Image Computing
    CountryAustralia
    CityHobart
    Period26/11/1328/11/13

    Fingerprint Dive into the research topics of 'Biometric Security Application for Person Authentication Using Retinal Vessel Feature'. Together they form a unique fingerprint.

    Cite this