Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis

Retinal blood vessels are significant anatomical structures in ophthalmic images. Automatic segmentation of blood vessels is one of the important steps in computer aided diagnosis system for the detection of diseases such as Diabetic Retinopathy that affect human retina. We propose a method for the segmentation of retinal blood vessels using Spatial Gabor filters as they can be tuned to the specific frequency and orientation. A new parameter is defined to facilitate filtering at different scales to detect the vessels of varying thicknesses. The method is tested on forty colour retinal images of DRIVE (Digital Retinal Images for Vessel Extraction) database with manual segmentations as ground truth. An overall accuracy of 84.22% is achieved for segmentation of retinal blood vessels.