Figure 20From: Structure-based level set method for automatic retinal vasculature segmentationVessel segmentation results for 700 × 605-pixel non-pathological and pathological images obtained from STARE dataset. Non-pathological image (a), and pathological image (b) (row 1). Manual segmentations of images (first observer) in row 1 (row 2), and segmented images (row 3).Back to article page