RETINA FUNDUS IMAGE MASK GENERATION USING PSEUDO PARAMETRIC MODELING TECHNIQUE

Abstract

The use of vascular intersection as one of the symptomsfor monitoring and diagnosis of diabetic retinopathy fromfundus images have been widely reported in literatures. Inthis work, a new hybrid approach that makes use of threedifferent methods of vascular intersection detection namelyModified cross-point number (MCN), Combine Cross Points(CNN) and Artificial Neural Network (ANN) is hereby proposed.Result obtained from the application of this techniqueto both simulated and experimental shows a very high accuracyand precision value in detecting both bifurcation andcross over points. Thus an improvement in bifurcation andvascular point detection and a good tool in the monitoringand diagnosis of diabetic retinopathy.