|
|
Publication
|
| Research Title |
Digital Image Processing Algorithms for Diagnosing Diabetic Retinopathy from Photography in Diabetes Patients |
| Date of Distribution |
15 January 2013 |
| Conference |
| Title of the Conference |
International Conference on Embedded Systems and Intelligent Technology |
| Organiser |
TESA, KKU |
| Conference Place |
Asawann Hotel |
| Province/State |
Nong Khai, Thailand |
| Conference Date |
13 January 2013 |
| To |
15 January 2013 |
| Proceeding Paper |
| Volume |
1 |
| Issue |
S09 |
| Page |
200-205 |
| Editors/edition/publisher |
|
| Abstract |
The purpose of this research was to develop algorithms for diagnosing and screening fundus photography in order to classify severity of Diabetic Retinopathy (DR). DR is an ocular complication of diabetic mellitus which can be divided into two stages. Early stage is Non-proliferative DR presented by microaneurysms, dot/blot hemorrhage, hard exudates, cotton-wool spot or venous beading. Post stage is Proliferative DR presented by neovascularization, pre-retina hemorrhage, vitreous hemorrhage or fibrous proliferation. In the study, combination of various digital image processing algorithms including image restoration and enhancement was used to improve image quality. Then, extractions of pathologies were implemented using segmentation and morphological techniques. Identified and localized objects were optic disk, fovea, macula and vessels. Classification of severity was performed by using feature extraction. Initial results indicated that the proposed technique yielded the classification accuracy more than 86%. |
| Author |
|
| Peer Review Status |
มีผู้ประเมินอิสระ |
| Level of Conference |
นานาชาติ |
| Type of Proceeding |
Full paper |
| Type of Presentation |
Oral |
| Part of thesis |
true |
| Presentation awarding |
false |
| Attach file |
|
| Citation |
0
|
|
|
|
|
|
|
|
|
Journal Publication
ไทย