Segmentation of hyperspectral images for the detection of rotten mandarins

The detection of rotten citrus in packing lines is carried out manually under ultraviolet illumination, which is dangerous for workers. Light emitted by the rotten region of the fruit due to the ultraviolet-induced fluorescence is used by the operator to detect the damages. This procedure is require...

Descripción completa

Detalles Bibliográficos
Autores principales: Gómez-Sanchís, Juan, Camps-Valls, G., Moltó, Enrique, Gomez-Chova, L., Aleixos, Nuria, Blasco, José
Otros Autores: Campilho, A. Kamel, M.
Formato: article
Lenguaje:Inglés
Publicado: 2017
Acceso en línea:http://hdl.handle.net/20.500.11939/5314
_version_ 1855032259514466304
author Gómez-Sanchís, Juan
Camps-Valls, G.
Moltó, Enrique
Gomez-Chova, L.
Aleixos, Nuria
Blasco, José
author2 Campilho, A. Kamel, M.
author_browse Aleixos, Nuria
Blasco, José
Campilho, A. Kamel, M.
Camps-Valls, G.
Gomez-Chova, L.
Gómez-Sanchís, Juan
Moltó, Enrique
author_facet Campilho, A. Kamel, M.
Gómez-Sanchís, Juan
Camps-Valls, G.
Moltó, Enrique
Gomez-Chova, L.
Aleixos, Nuria
Blasco, José
author_sort Gómez-Sanchís, Juan
collection ReDivia
description The detection of rotten citrus in packing lines is carried out manually under ultraviolet illumination, which is dangerous for workers. Light emitted by the rotten region of the fruit due to the ultraviolet-induced fluorescence is used by the operator to detect the damages. This procedure is required because the low contrast between the damaged and sound skin under visible illumination difficult their detection. We study a set of techniques aimed to detect rottenness in citrus using visible and near infrared lighting trough an hyperspectral imaging system. Methods for selecting a proper set of wavelengths are investigated such as correlation analysis, mutual information, stepwise or genetic algorithms. The image segmentation relies on the combination of band selection techniques and pixel classification methods such as classification and regression trees and linear discriminant analysis.
format article
id ReDivia5314
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2017
publishDateRange 2017
publishDateSort 2017
record_format dspace
spelling ReDivia53142025-04-25T14:52:07Z Segmentation of hyperspectral images for the detection of rotten mandarins Lecture Notes in Computer Science Gómez-Sanchís, Juan Camps-Valls, G. Moltó, Enrique Gomez-Chova, L. Aleixos, Nuria Blasco, José Campilho, A. Kamel, M. The detection of rotten citrus in packing lines is carried out manually under ultraviolet illumination, which is dangerous for workers. Light emitted by the rotten region of the fruit due to the ultraviolet-induced fluorescence is used by the operator to detect the damages. This procedure is required because the low contrast between the damaged and sound skin under visible illumination difficult their detection. We study a set of techniques aimed to detect rottenness in citrus using visible and near infrared lighting trough an hyperspectral imaging system. Methods for selecting a proper set of wavelengths are investigated such as correlation analysis, mutual information, stepwise or genetic algorithms. The image segmentation relies on the combination of band selection techniques and pixel classification methods such as classification and regression trees and linear discriminant analysis. 2017-06-01T10:12:07Z 2017-06-01T10:12:07Z 2008 2008 article Gómez-Sanchis J., Camps-Valls G., Moltó E., Gómez-Chova L., Aleixos N., Blasco J. (2008) Segmentation of Hyperspectral Images for the Detection of Rotten Mandarins. In: Campilho A., Kamel M. (eds) Image Analysis and Recognition. ICIAR 2008. Lecture Notes in Computer Science, vol 5112. Springer, Berlin, Heidelberg, pp. 1071-1080. 0302-9743; 978-3-540-69811-1 http://hdl.handle.net/20.500.11939/5314 10.1007/978-3-540-69812-8_107 en openAccess Impreso
spellingShingle Gómez-Sanchís, Juan
Camps-Valls, G.
Moltó, Enrique
Gomez-Chova, L.
Aleixos, Nuria
Blasco, José
Segmentation of hyperspectral images for the detection of rotten mandarins
title Segmentation of hyperspectral images for the detection of rotten mandarins
title_full Segmentation of hyperspectral images for the detection of rotten mandarins
title_fullStr Segmentation of hyperspectral images for the detection of rotten mandarins
title_full_unstemmed Segmentation of hyperspectral images for the detection of rotten mandarins
title_short Segmentation of hyperspectral images for the detection of rotten mandarins
title_sort segmentation of hyperspectral images for the detection of rotten mandarins
url http://hdl.handle.net/20.500.11939/5314
work_keys_str_mv AT gomezsanchisjuan segmentationofhyperspectralimagesforthedetectionofrottenmandarins
AT campsvallsg segmentationofhyperspectralimagesforthedetectionofrottenmandarins
AT moltoenrique segmentationofhyperspectralimagesforthedetectionofrottenmandarins
AT gomezchoval segmentationofhyperspectralimagesforthedetectionofrottenmandarins
AT aleixosnuria segmentationofhyperspectralimagesforthedetectionofrottenmandarins
AT blascojose segmentationofhyperspectralimagesforthedetectionofrottenmandarins
AT gomezsanchisjuan lecturenotesincomputerscience
AT campsvallsg lecturenotesincomputerscience
AT moltoenrique lecturenotesincomputerscience
AT gomezchoval lecturenotesincomputerscience
AT aleixosnuria lecturenotesincomputerscience
AT blascojose lecturenotesincomputerscience