Automated Segmentation of Retinal Blood Vessels

Abstract

Digital image processing and the image analysis technology based on the advances in microelectronics and computer have many applications in biology. In clinical ophthalmology, study of blood vessels in retina is important for detection of the diseases.  Diabetic retinopathy is one of the diseases which damages the retina and leads to blindness. Manual diagnosis of analyzing images from a patient with Diabetic Retinopathy increases the time. Automatic segmentation of retinal blood vessels could save workload of the ophthalmologists and may assist in characterizing the defected lesions and to identify false positives with high accuracy. The proposed algorithm uses optimized Gabor filter with local entropy thresholding. The blood vessel detection and segmentation is important for diabetic retinopathy diagnosis at earlier stage. The proposed method detects blood vessels with higher accuracy and sensitivity in the retinal images. The DRIVE database has been used to enable comparative studies on segmentation of blood vessels in retinal images.