University of Tasmania
Browse

Feature extraction for classification from images: a look at the retina

Version 2 2024-09-17, 02:02
Version 1 2023-05-23, 04:16
conference contribution
posted on 2024-09-17, 02:02 authored by FCH Chui, Ivan BindoffIvan Bindoff, RN Williams, Byeong KangByeong Kang
A method is proposed for the representation of localised features using disjoint sub-images taken from several datasets of retinal images for use within an incremental learning system. A tile-based localised adaptive threshold selection method was taken for vessel segmentation based on separate colour components. Arteriole-venous differentiation was done using the composite of these components and high quality fundal images. Vessel segmentation performance was evaluated on the DRIVE and STARE datasets achieving average specificity of 0.9379 and sensitivity of 0.5924. © 2008 IEEE.

History

Publication title

Proceedings of 2008 International Symposium on Ubiquitous Multimedia Computing

Volume

2007

Editors

Ceballos, S

Pagination

93-98

ISBN

978-0-7695-3427-5

Department/School

Information and Communication Technology

Publisher

IEEE Computer Society Conference Publishing Services (CPS)

Publication status

  • Published

Place of publication

Piscataway, NJ

Event title

International Symposium on Ubiquitous Multimedia Computing (UMC)

Event Venue

Hobart, Tasmania

Date of Event (Start Date)

2008-10-13

Date of Event (End Date)

2008-10-15

Socio-economic Objectives

280115 Expanding knowledge in the information and computing sciences

Usage metrics

    University Of Tasmania

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC