Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach

One of the main problems in the post-harvest processing of citrus is the detection of visual defects in order to classify the fruit depending on their appearance. Species and cultivars of citrus present a high rate of unpredictability in texture and colour that makes it difficult to develop a genera...

Descripción completa

Detalles Bibliográficos
Autores principales: López-García, Fernando, Andreu-Garcia, Gabriela, Blasco, José, Aleixos, Nuria, Valiente, José Miguel
Formato: Artículo
Lenguaje:Inglés
Publicado: 2017
Acceso en línea:http://hdl.handle.net/20.500.11939/5531
_version_ 1855491940961746944
author López-García, Fernando
Andreu-Garcia, Gabriela
Blasco, José
Aleixos, Nuria
Valiente, José Miguel
author_browse Aleixos, Nuria
Andreu-Garcia, Gabriela
Blasco, José
López-García, Fernando
Valiente, José Miguel
author_facet López-García, Fernando
Andreu-Garcia, Gabriela
Blasco, José
Aleixos, Nuria
Valiente, José Miguel
author_sort López-García, Fernando
collection ReDivia
description One of the main problems in the post-harvest processing of citrus is the detection of visual defects in order to classify the fruit depending on their appearance. Species and cultivars of citrus present a high rate of unpredictability in texture and colour that makes it difficult to develop a general, unsupervised method able of perform this task. In this paper we study the use of a general approach that was originally developed for the detection of defects in random colour textures. It is based on a Multivariate Image Analysis strategy and uses Principal Component Analysis to extract a reference eigenspace from a matrix built by unfolding colour and spatial data from samples of defect-free peel. Test images are also unfolded and projected onto the reference eigenspace and the result is a score matrix which is used to compute defective maps based on the T(2) statistic. In addition, a multiresolution scheme is introduced in the original method to speed up the process. Unlike the techniques commonly used for the detection of defects in fruits, this is an unsupervised method that only needs a few samples to be trained. It is also a simple approach that is suitable for real-time compliance. Experimental work was performed on 120 samples of oranges and mandarins from four different cultivars: Clemenules, Marisol. Fortune, and Valencia. The success ratio for the detection of individual defects was 91.5%, while the classification ratio of damaged/sound samples was 94.2%. These results show that the studied method can be suitable for the task of citrus inspection. (C) 2010 Elsevier B.V. All rights reserved.
format Artículo
id ReDivia5531
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2017
publishDateRange 2017
publishDateSort 2017
record_format dspace
spelling ReDivia55312025-04-25T14:43:13Z Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach López-García, Fernando Andreu-Garcia, Gabriela Blasco, José Aleixos, Nuria Valiente, José Miguel One of the main problems in the post-harvest processing of citrus is the detection of visual defects in order to classify the fruit depending on their appearance. Species and cultivars of citrus present a high rate of unpredictability in texture and colour that makes it difficult to develop a general, unsupervised method able of perform this task. In this paper we study the use of a general approach that was originally developed for the detection of defects in random colour textures. It is based on a Multivariate Image Analysis strategy and uses Principal Component Analysis to extract a reference eigenspace from a matrix built by unfolding colour and spatial data from samples of defect-free peel. Test images are also unfolded and projected onto the reference eigenspace and the result is a score matrix which is used to compute defective maps based on the T(2) statistic. In addition, a multiresolution scheme is introduced in the original method to speed up the process. Unlike the techniques commonly used for the detection of defects in fruits, this is an unsupervised method that only needs a few samples to be trained. It is also a simple approach that is suitable for real-time compliance. Experimental work was performed on 120 samples of oranges and mandarins from four different cultivars: Clemenules, Marisol. Fortune, and Valencia. The success ratio for the detection of individual defects was 91.5%, while the classification ratio of damaged/sound samples was 94.2%. These results show that the studied method can be suitable for the task of citrus inspection. (C) 2010 Elsevier B.V. All rights reserved. 2017-06-01T10:12:31Z 2017-06-01T10:12:31Z 2010 MAY 2010 article acceptedVersion Lopez-Garcia, F., Andreu-Garcia, Gabriela, Blasco, J., Aleixos, N., Valiente, J.M. (2010). Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach. Computers and Electronics in Agriculture, 71(2), 189-197. 0168-1699 http://hdl.handle.net/20.500.11939/5531 10.1016/j.compag.2010.02.001 en openAccess Impreso
spellingShingle López-García, Fernando
Andreu-Garcia, Gabriela
Blasco, José
Aleixos, Nuria
Valiente, José Miguel
Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
title Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
title_full Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
title_fullStr Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
title_full_unstemmed Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
title_short Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
title_sort automatic detection of skin defects in citrus fruits using a multivariate image analysis approach
url http://hdl.handle.net/20.500.11939/5531
work_keys_str_mv AT lopezgarciafernando automaticdetectionofskindefectsincitrusfruitsusingamultivariateimageanalysisapproach
AT andreugarciagabriela automaticdetectionofskindefectsincitrusfruitsusingamultivariateimageanalysisapproach
AT blascojose automaticdetectionofskindefectsincitrusfruitsusingamultivariateimageanalysisapproach
AT aleixosnuria automaticdetectionofskindefectsincitrusfruitsusingamultivariateimageanalysisapproach
AT valientejosemiguel automaticdetectionofskindefectsincitrusfruitsusingamultivariateimageanalysisapproach