• Français
    • English
  • Français 
    • Français
    • English
  • Login
View Document 
  •   Savoirs UdeS Home
  • Sciences
  • Sciences – Mémoires
  • View Document
  •   Savoirs UdeS Home
  • Sciences
  • Sciences – Mémoires
  • View Document
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

All of Savoirs UdeSDomains & CollectionsBy Issue DateAuthorsTitlesSubjectsDirectorsThis CollectionBy Issue DateAuthorsTitlesSubjectsDirectors

My Account

Login

Statistics

View Usage Statistics

Detection of micro-aneurysms in low-resolution color retinal images

Thumbnail
View/Open
MQ74560.pdf (1.626Mb)
Publication date
2001
Author(s)
Yang, Guang
Show full document record
Abstract
Diabetic retinopathy is the most common cause of blindness in the industrial countries. The best way to prevent visual losses from diabetes is early detection. From photographic and angiographic images, an experienced physician can find a lot of useful information to assess the development and progression of diabetic retinopathy, but this procedure is time-consuming. Automatic detection of indicators of diabetic retinopathy is a more efficient method. The goal of this project is to develop and optimize an algorithm to detect micro-aneurysms and small round hemorrhages in low-resolution color retinal images. Our algorithm is adapted from a micro-aneurysm detector developed for high-resolution angiographic films. It consists of pre-processing, morphological filtering, thresholding, region growing and feature analysis. This algorithm has been tested on retinal images of 640 x 480 resolution. Experimental results show that it is possible to set up parameters to achieve 100% global sensitivity with up to 80% global specificity, which means that all affected individuals could be directed to specialists without too much overload.
URI
http://savoirs.usherbrooke.ca/handle/11143/4546
Collection
  • Sciences – Mémoires [1603]

DSpace software [version 5.4 XMLUI], copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
 

 


DSpace software [version 5.4 XMLUI], copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback