A Highly Accurate and Robust Retinal Vessel Segmentation Algorithm
Date
2015-12-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
ORCID
Type
Thesis
Degree Level
Masters
Abstract
Retinal vessel segmentation is beneficial for eye surgery and detection of diabetic retinopathy. Mathematical morphology, or top-hat reconstruction can keep desired vessel structures. Gaussian mixture model is used here to build classification model and generate binary images of retinal vessels. After experimental testing, this work achieves the best vessel tracking ability and robustness performance.
Description
Keywords
Retinal segmentation, mathematical morphology, Gaussian mixture model
Citation
Degree
Master of Science (M.Sc.)
Department
Electrical and Computer Engineering
Program
Electrical Engineering