Retinal Blood Vessel Segmentation From Fundus Image- MATLAB PROJECTS CODE
Digital images are obtained from the retina and graded by trained professionals. Progression of diabetic retinopathy is assessed by its severity, which in turn determines the frequency of examinations. However, a significant shortage of professional observers has prompted computer assisted monitoring.
Assessment of blood vessels network plays an important role in a variety of medical disorders. Manifestations of several vascular disorders, such as diabetic retinopathy, depend on detection of the blood vessels network. In this work green channel of the fundus RGB image was used for obtaining the traces of blood vessels. The algorithm developed used morphological operation to smoothen the background, allowing veins, to be seen clearly. Disc structuring elements were used in this work. The proposed algorithm has employed modules such as contrast enhancement, background exclusion and thresholding.
The techniques describe in the paper is based on morphological operation and apply on publicly available DRIVE, diaretdb0, diaretdb1 databases and images from eye hospital. Experimental results obtained by using gray-scale/green-channel images have been presented. The proposed algorithm has been shown to be a highly effective method for classifying retinal blood vessels. The proposed algorithm being simple and easy to implement, is best suited for fast processing applications.