Fast segmentation of retinal blood vessels using a deformable contour

This paper presents a deformable contour based method for blood vessel segmentation in digital retinal images. The method was evaluated on the publicly available DRIVE database, widely used for this purpose, since it contains retinal images where the vascular structure has been precisely marked by experts. Method performance is comparable to other existing solutions in literature, but it reaches the result faster than the others. Its effectiveness and velocity make this blood vessel segmentation technique suitable for retinal image computer analysis such as automated screening for early diabetic retinopathy detection.

keywords: Vessels segmentation, retinal imaging, deformable contour