In this paper is proposed, implemented and evaluated a novel radial basis probabilistic neuralnetwork (RBPNN) based classification algorithm for classification fruit surface defects in color andtexture of a very important fruit as orange. The proposed algorithm takes orange images as inputsthen the texture and gray features of defect area are extracted by computing a gray level co-occurrencematrix and the defect areas are classified through an RBPNN-based classifier. Theconducted experiments and the results reveal as the classification accuracy achieved is up to 88%.

A novel neural networks-based texture image processing algorithm for orange defects classification / Capizzi, G; Lo Sciuto, G; Napoli, C; Tramontana, E; Woźniak, M. - In: INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS. - ISSN 2158-107X. - 13:2(2016), pp. 45-60.

A novel neural networks-based texture image processing algorithm for orange defects classification

Napoli C
;
2016

Abstract

In this paper is proposed, implemented and evaluated a novel radial basis probabilistic neuralnetwork (RBPNN) based classification algorithm for classification fruit surface defects in color andtexture of a very important fruit as orange. The proposed algorithm takes orange images as inputsthen the texture and gray features of defect area are extracted by computing a gray level co-occurrencematrix and the defect areas are classified through an RBPNN-based classifier. Theconducted experiments and the results reveal as the classification accuracy achieved is up to 88%.
2016
Neural Networks; Pattern Recognition; Texture Analysis
01 Pubblicazione su rivista::01a Articolo in rivista
A novel neural networks-based texture image processing algorithm for orange defects classification / Capizzi, G; Lo Sciuto, G; Napoli, C; Tramontana, E; Woźniak, M. - In: INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS. - ISSN 2158-107X. - 13:2(2016), pp. 45-60.
File allegati a questo prodotto
File Dimensione Formato  
Capizzi_A-novel-neural_2016.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 268.18 kB
Formato Adobe PDF
268.18 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1328557
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 52
  • ???jsp.display-item.citation.isi??? ND
social impact