Automatic grading of Bi-colored apples by multispectral machine vision

Unay, Devrim; Gosselin, Bernard; Kleynen, Olivier; Leemans, Vincent; Destain, Marie-France; Debeir, Olivier

doi:10.1016/j.compag.2010.11.006

Reference : Automatic grading of Bi-colored apples by multispectral machine vision


	Document type :	Scientific journals : Article
	Discipline(s) :	Engineering, computing & technology : Multidisciplinary, general & others Life sciences : Agriculture & agronomy
	To cite this reference:	http://hdl.handle.net/2268/81208

Title :	Automatic grading of Bi-colored apples by multispectral machine vision
Language :	English
Author, co-author :	Unay, Devrim [> >]
	Gosselin, Bernard [> >]
	Kleynen, Olivier [> >]
	Leemans, Vincent [Université de Liège - ULiège > Sciences et technologie de l'environnement > Mécanique et construction >]
	Destain, Marie-France [Université de Liège - ULiège > Sciences et technologie de l'environnement > Mécanique et construction >]
	Debeir, Olivier [> >]
Publication date :	2011
Journal title :	Computers & Electronics in Agriculture
Publisher :	Elsevier Science
Peer reviewed :	Yes (verified by ORBi)
Audience :	International
ISSN :	0168-1699
Keywords :	[en] Fruit grading ; Defect detection ; Multispectral images ; Feature extraction ; Feature selection ; Classification
Abstract :	[en] In this paper we present a novel application work for grading of apple fruits by machine vision. Following precise segmentation of defects by minimal confusion with stem/calyx areas on multispectral images, statistical, textural and geometric features are extracted from the segmented area. Using these features, statistical and syntactical classifiers are trained for two- and multi-category grading of the fruits. Results showed that feature selection provided improved performance by retaining only the important features, and statistical classifiers outperformed their syntactical counterparts. Compared to the state-of-the-art, our two-category grading solution achieved better recognition rates (93.5% overall accuracy). In this work we further provided a more realistic multi-category grading solution, where different classification architectures are evaluated. Our observations showed that the single-classifier architecture is computationally less demanding, while the cascaded one is more accurate.
Funders :	Région wallonne : Direction générale des Technologies, de la Recherche et de l'Energie - DGTRE
Target :	Researchers
Permalink :	http://hdl.handle.net/2268/81208
DOI :	10.1016/j.compag.2010.11.006

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	Compag10.pdf		Author postprint	816.96 kB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5