Feature extraction for classification from images: a look at the retina
Version 2 2024-09-17, 02:02Version 2 2024-09-17, 02:02
Version 1 2023-05-23, 04:16Version 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 KangA 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 ComputingVolume
2007Editors
Ceballos, SPagination
93-98ISBN
978-0-7695-3427-5Department/School
Information and Communication TechnologyPublisher
IEEE Computer Society Conference Publishing Services (CPS)Publication status
- Published
Place of publication
Piscataway, NJEvent title
International Symposium on Ubiquitous Multimedia Computing (UMC)Event Venue
Hobart, TasmaniaDate of Event (Start Date)
2008-10-13Date of Event (End Date)
2008-10-15Socio-economic Objectives
280115 Expanding knowledge in the information and computing sciencesUsage metrics
Categories
Keywords
Licence
Exports
RefWorksRefWorks
BibTeXBibTeX
Ref. managerRef. manager
EndnoteEndnote
DataCiteDataCite
NLMNLM
DCDC