Precise retinal vessels localization is an important and challenging task. Segmentationof retinal blood vessels becomes more difficult in abnormal images with the presenceof diseases like hypertension, diabetes, stroke and other vascular disorders. In thiswork, a new fast framework for automatic retinal blood vessels extraction and denoisinghas been proposed. Green channel due to its prominent vessel structure is used as an inputto morphological filters to eradicate low frequency noise or

more »

... rical entities, e.g.,macula, optic disk and other abnormalities. The Generalized Linear Model (GLM) regressionis used for non-uniform contrast enhancement followed by Frangi filter for vasculaturebased enhancement. Masking operation has performed to extract Region of Interest(ROI) for application of moment-preserving thresholding to separate vessel andbackground pixels. Finally, postprocessing steps are applied to eliminate unconnectedpixels and to obtain final binary image. This technique has been validated on the DRIVEand the STARE databases and contested with other competing techniques. Experimentalresults indicate that the proposed vessel extraction framework outperforms many recentexisting methods published in literature.