Abstract: This paper introduced a supervised method for blood vessel detection in digital color retinal images. Neural network (NN) scheme is used for pixel classification and computes a 7-D vector composed of gray-level and moment invariants-based features for pixel representation. DRIVE databases are used for this purpose. Segmentation of blood vessels in retinal images allows early diagnosis of diseases. The results are encouraging and will be used for further application such as personal identification and are evaluated in terms of sensitivity and specificity and accuracy.
Keywords: Diabetic retinopathy, moment invariants, retinal blood vessel segmentation, gray level features.
Title: DETECTING AND SEGMENTING DIGITAL RETINAL BLOOD VESSELS USING NEURAL NETWORK
Author: Nafeela Jahan.N
Research Publish Journals
