Article (Scientific journals)
Defect segmentation on 'Jonagold' apples using colour vision and a Bayesian classification method
Leemans, Vincent; Magein, Hugo; Destain, Marie-France
1999In Computers and Electronics in Agriculture, 23 (1), p. 43-53
Peer Reviewed verified by ORBi
 

Files


Full Text
CEA99O.pdf
Author preprint (694.5 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
apple defects; bi-colour fruit; colour vision; computer vision; image segmentation
Abstract :
[en] This paper shows how the information enclosed in a colour image of a bi-colour apple can be used to segment defects. A method to segment pixels, based on a Bayesian classification process, is proposed. The colour frequency distributions of the healthy tissue and of the defects were used to estimate the probability distribution of each class. The results showed that most defects, namely bitter pit, fungi attack, scar tissue, frost damages, bruises, insect attack and scab, are segmented. However, russet was sometimes confused with the transition area between ground and blush colour. (C) 1999 Elsevier Science B.V. All rights reserved.
Disciplines :
Agriculture & agronomy
Computer science
Author, co-author :
Leemans, Vincent ;  Université de Liège - ULiège > Gembloux Agro-Bio Tech > Gembloux Agro-Bio Tech
Magein, Hugo ;  Université de Liège - ULiège > Gembloux Agro-Bio Tech > Gembloux Agro-Bio Tech
Destain, Marie-France ;  Université de Liège - ULiège > Gembloux Agro-Bio Tech > Gembloux Agro-Bio Tech
Language :
English
Title :
Defect segmentation on 'Jonagold' apples using colour vision and a Bayesian classification method
Publication date :
1999
Journal title :
Computers and Electronics in Agriculture
ISSN :
0168-1699
eISSN :
1872-7107
Publisher :
Elsevier Science
Volume :
23
Issue :
1
Pages :
43-53
Peer reviewed :
Peer Reviewed verified by ORBi
Available on ORBi :
since 30 November 2009

Statistics


Number of views
127 (11 by ULiège)
Number of downloads
309 (5 by ULiège)

Scopus citations®
 
95
Scopus citations®
without self-citations
90
OpenCitations
 
62

Bibliography


Similar publications



Contact ORBi