National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Microaneurysms and hemorrhages detection in retinal images
Tobiášová, Nela ; Štohanzlová, Petra (referee) ; Kolář, Radim (advisor)
Diabetic retinopathy is a serious eye complication of diabetes mellitus and one of the major causes of blindness in the world. The microaneurysms and the haemorrhages are the pathologies of diabetic retinopathy. Their detection can halt or reverse the progression of this disease and prevent blindness. The algorithms could be helpful to ophthalmologists. This bacherol’s thesis is concerned with the detection of microaneurysms and haemorrhages in fundus images. The diabetic retinopathy, the types of lesions and the treatment methods are described in the first part of the paper. Existing methods are described as follows. The practical part of this work is aimed at the proposal and the detection of the red lesions. It consists of several steps, such as selecting the correct channel of RGB images, using local methods of contrast enhancement, edge detection, thresholding, creating a training set of the feature vector and the classification with the use of the neutral network.
Microaneurysms and hemorrhages detection in retinal images
Tobiášová, Nela ; Štohanzlová, Petra (referee) ; Kolář, Radim (advisor)
Diabetic retinopathy is a serious eye complication of diabetes mellitus and one of the major causes of blindness in the world. The microaneurysms and the haemorrhages are the pathologies of diabetic retinopathy. Their detection can halt or reverse the progression of this disease and prevent blindness. The algorithms could be helpful to ophthalmologists. This bacherol’s thesis is concerned with the detection of microaneurysms and haemorrhages in fundus images. The diabetic retinopathy, the types of lesions and the treatment methods are described in the first part of the paper. Existing methods are described as follows. The practical part of this work is aimed at the proposal and the detection of the red lesions. It consists of several steps, such as selecting the correct channel of RGB images, using local methods of contrast enhancement, edge detection, thresholding, creating a training set of the feature vector and the classification with the use of the neutral network.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.