Diagnosis of Diabetic Retenopathy using Blood Vessel Segmentation and Pattern Recognition Techniques

This paper presents a new method for blood vessel detection in digital retinal images. This method uses a mathematical morphology scheme for pixel classification and computes segmented blood vessels by using morphological operations. The method proves especially accurate for vessel detection in DIARETDB0 and DIARETDB1 images. Its effectiveness and robustness with different image conditions, together with its simplicity and fast implementation, make this blood vessel segmentation proposal suitable for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.