1 AIT Asian Institute of Technology

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

AuthorYin Aye Moe
Call NumberAIT Thesis no.CS-07-02
Subject(s)Diabetic retinopathy
Image processing--Digital techniques

NoteA thesis submitted in partial fulfillment of the requirements for the degree of Master of Science, School of Engineering and Technology
PublisherAsian Institute of Technology
Series StatementThesis ; no. CS-07-02
AbstractDiabetic 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 (SYM) classifier is applied to classify exudates and nonexudates.
Year2007
Corresponding Series Added EntryAsian Institute of Technology. Thesis ; no. CS-07-02
TypeThesis
SchoolSchool of Engineering and Technology (SET)
DepartmentDepartment of Information and Communications Technologies (DICT)
Academic Program/FoSComputer Science (CS)
Chairperson(s)Dailey, Matthew N.;
Examination Committee(s)Guha, Sumanta;Bunyarit Uyyanonvara;
Scholarship Donor(s)Asian Institute of Technology Fellowship;
DegreeThesis (M.Sc.) - Asian Institute of Technology, 2007


Usage Metrics
View Detail0
Read PDF0
Download PDF0