In the field of diabetic retinopathies attention has been recently focused on the problem of obtaining an accurate diabetic ocular diagnosis. In this paper a contribution in the detection of diabetic symptoms using contrast enhancement of fundus images is proposed by synthesizing an “ad hoc” neurofuzzy system. A fuzzy technique is considered to develop a suitable coding of fuzzy rules. A sparsely-connected neural network is then synthesized to provide enhanced contrast retinal images with bimodal histograms. Experimental examples are reported
A Hybrid Neurofuzzy System for Contrast Enhancement of Fundus Images in Diabetic Retinopathies
Carnimeo, Leonarda;Giaquinto, Antonio
2006-01-01
Abstract
In the field of diabetic retinopathies attention has been recently focused on the problem of obtaining an accurate diabetic ocular diagnosis. In this paper a contribution in the detection of diabetic symptoms using contrast enhancement of fundus images is proposed by synthesizing an “ad hoc” neurofuzzy system. A fuzzy technique is considered to develop a suitable coding of fuzzy rules. A sparsely-connected neural network is then synthesized to provide enhanced contrast retinal images with bimodal histograms. Experimental examples are reportedFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.