In this work a Voting Procedure supported by a Neural Validity Classifier for assuring a correct localization of the reference point of optic disk in retinal imaging is proposed. A multiple procedure with multiple resulting points is briefly described. A Neural Network behaving as a Validity Classifier of regular/abnormal solutions is then synthesized to validate the adequacy of the resulting midpoints as candidate reference points. A Voting Procedure, supported by the synthesized Neural Validity Classifier, is successively performed, by comparing only candidate pixels classified as valid ones. In this way, the most suitable and reliable candidate can be voted to be adopted as the reference point of OD in successive retinal analyses.
A Voting Procedure Supported by a Neural Validity Classifier for Optic Disk Detection / Carnimeo, Leonarda; Cinzia Benedetto, Anna; Mastronardi, Giuseppe (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: Emerging Intelligent Computing Technology and Applications : 8th International Conference, ICIC 2012. Huangshan, China, July 25-29, 2012. Proceedings / [a cura di] De-Shuang Huang, Phalguni Gupta, Xiang Zhang, Prashan Premaratne. - STAMPA. - Berlin, Heidelberg : Springer, 2012. - ISBN 978-3-642-31836-8. - pp. 467-474 [10.1007/978-3-642-31837-5_68]
A Voting Procedure Supported by a Neural Validity Classifier for Optic Disk Detection
Leonarda Carnimeo;Giuseppe Mastronardi
2012-01-01
Abstract
In this work a Voting Procedure supported by a Neural Validity Classifier for assuring a correct localization of the reference point of optic disk in retinal imaging is proposed. A multiple procedure with multiple resulting points is briefly described. A Neural Network behaving as a Validity Classifier of regular/abnormal solutions is then synthesized to validate the adequacy of the resulting midpoints as candidate reference points. A Voting Procedure, supported by the synthesized Neural Validity Classifier, is successively performed, by comparing only candidate pixels classified as valid ones. In this way, the most suitable and reliable candidate can be voted to be adopted as the reference point of OD in successive retinal analyses.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
