DSpace Repository

Machine learning appraoch to automatic exudate detection in retinal images of diabetic patients

Show simple item record

dc.contributor.advisor Dailey, Matthew N. (Chairperson) en_US
dc.contributor.author Yin Aye Moe en_US
dc.date.accessioned 2015-01-12T10:40:43Z
dc.date.available 2015-01-12T10:40:43Z
dc.date.issued 2007-05 en_US
dc.identifier.other AIT Thesis no.CS-07-02 en_US
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/345
dc.description 7 p. en_US
dc.description.abstract Diabetic Retinopathy (DR) is the commonest cause of vision loss in the world. Early detection and treatment of these diseases are crucial to avoid preventable vision loss and blindness. To lower the cost of detection, we employ machine learning approach to detect automatically the presence of abnormalities in the retinal images. The research in this thesis focuses on one of the abnormal signs that is, the presence of exudates, also called lesions, in the retinal images. This system examines the retinal images and presents only those containing exudates to the ophthalmologists. In this manner, the total workload of ophthalmologists can be reduced. In order to detect exudates, a three-stage approach is applied to detect and classify bright lesions. After preprocessing stage, Difference-of-Gaussian (DoG) filters are applied to extract the features of images. Finally, support vector machine (SVM) classifier is applied to classify exudates and nonexudates. en_US
dc.description.sponsorship AIT Fellowship en_US
dc.language.iso en en_US
dc.publisher Asian Institute of Technology en_US
dc.relation.ispartofseries AIT Publications; en_US
dc.subject Diabetic retinopathy en_US
dc.subject Image processing -- Digital techniques en_US
dc.title Machine learning appraoch to automatic exudate detection in retinal images of diabetic patients en_US
dc.type Thesis en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account