Abstract:
This document is focused on image recognition methods that are suitable to be used for diagnostic purposes in ophthalmology. Particularly it is an identification of brigh...Show MoreMetadata
Abstract:
This document is focused on image recognition methods that are suitable to be used for diagnostic purposes in ophthalmology. Particularly it is an identification of bright lesions in fundus images that are side effect of disease called diabetic retinopathy. For recognition purposes we used method Support Vector Machine (SVM). Diabetic retinopathy, fundus images database and also SVM are briefly described in theoretical introduction. Next part of work consists of methodology used for image processing, where steps that we used to solve our issue are summarized. Last part is dedicated to achieved results and evaluation whether given method is suitable for patient's screening.
Published in: 2016 International Symposium ELMAR
Date of Conference: 12-14 September 2016
Date Added to IEEE Xplore: 03 November 2016
ISBN Information:
Print ISSN: 1334-2630