Detection of exudates in diabetic retinopathy images using boosting based algorithms

Abstract

ABSTRACT Diabetic retinopathy is a leading cause of vision loss in developed countries. Regular diabetic retinal eye screenings are needed to detect early signs of retinopathy, so that appropriate treatments can be rendered to prevent blindness. Digital imaging is becoming available as a means of screening for diabetic retinopathy. However, with the large number of patients undergoing screenings, medical professionals require a tremendous amount of time and effort in order to analyse and diagnose the fundus photo-graphs, the treatment is done on a digital image, to obtain results as complex as recognizing patterns or as simple as enhancing con-tours, may involve filtering, transformations of gray levels, based on histogram processing, describing, between others. The design of a teaching tool to facilitate image processing, allowing access to each of the steps involved in the system, ensure the achievement of good results supported the implementation of parameterized and interactive techniques supported. In the classification of pathological images is the marking of the images to see them done after the pre-processing, which are marked to be admitted to the boosting algorithm, is used mainly variant gentleBoost, and supported in the basic concepts of image processing.