Diabetic retinopathy (DR) is a complication seen in individuals with diabetes and is a condition marked by high levels of blood glucose. The current project presents an efficient automated diabetic retinopathy detection system, which identifies blood vessel leaks (known as exudates) in digital images of the fundus. This system detects and classifies exudates into two types: soft and hard. The project also presents and compares three techniques used for enhancing a digital fundus image: The Histogram Equalization (HE), the Contrast Limited Adaptive Histogram Equalization (CLAHE), and the Mahalanobis Distance (MD). Experimental results show that the MD-based technique is the best method for accurate and efficient detection and classification of exudates in a digital fundus image. The proposed system can assist ophthalmologists in monitoring the evolution of diabetic retinopathy, and implement interventions and treatment to preserve vision in patients with diabetes.
|Commitee:||Khoo, I-Hung, Yeh, Hen-Geul|
|School:||California State University, Long Beach|
|School Location:||United States -- California|
|Source:||MAI 56/04M(E), Masters Abstracts International|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be