Figure 18From: Structure-based level set method for automatic retinal vasculature segmentationVessel segmentation results for 565 × 584-pixel pathological and non-pathological images obtained from DRIVE dataset. Pathological image (a), non-pathological image (b), and another non-pathological image (c) (row 1). Manual segmentations of images in row 1 (row 2). Segmented images (row 3).Back to article page