Show simple item record

dc.creatorBlanch Pérez del Notario, Carolinaes_ES
dc.creatorLópez Molina, Carloses_ES
dc.creatorLambrechts, Andyes_ES
dc.creatorSaeys, Wouteres_ES
dc.date.accessioned2021-06-14T11:17:38Z
dc.date.available2021-06-14T11:17:38Z
dc.date.issued2020
dc.identifier.issn2040-4565
dc.identifier.urihttps://hdl.handle.net/2454/39913
dc.descriptionIncluye material complementarioes_ES
dc.description.abstractThe discrimination power of a hyperspectral imaging system for image segmentation or object detection is determined by the illumination, the camera spatial–spectral resolution, and both the pre-processing and analysis methods used for image processing. In this study, we methodically reviewed the alternatives for each of those factors for a case study from the food industry to provide guidance in the construction and configuration of hyperspectral imaging systems in the visible near infrared range for food quality inspection. We investigated both halogen-and LED-based illuminations and considered cameras with different spatial–spectral resolution trade-offs. At the level of the data analysis, we evaluated the impact of binning, median filtering and bilateral filtering as pre-or post-processing and compared pixel-based classifiers with convolutional neural networks for a challenging application in the food industry, namely ingredient identification in a flour–seed mix. Starting from a basic configuration and by modifying the combination of system aspects we were able to increase the mean accuracy by at least 25%. In addition, different trade-offs in performance-complexity were identified for different combinations of system parameters, allowing adaptation to diverse application requirements.en
dc.description.sponsorshipThis work was carried out in the context of the iFAST project with the support from Flanders’ FOOD and VLAIO (Agentschap Innoveren & Ondernemen), research and innovation program under grant agreement No. 140992.en
dc.format.extent17 p.
dc.format.mimetypeapplication/pdfen
dc.language.isoengen
dc.publisherIM Publicationsen
dc.relation.ispartofJournal of Spectral Imaging, g 9, a16 (2020)en
dc.rights© 2020 The Authors. This work is licensed under a Creative Commons BY-NC-ND Licence.en
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectClassification accuracyen
dc.subjectConvolutional neural networksen
dc.subjectHyperspectralen
dc.subjectIlluminationen
dc.subjectPre-and post-processingen
dc.subjectSpatial–spectral resolutionen
dc.subjectSystem parametersen
dc.titleHyperspectral system trade-offs for illumination, hardware and analysis methods: a case study of seed mix ingredient discriminationen
dc.typeinfo:eu-repo/semantics/articleen
dc.typeArtículo / Artikuluaes
dc.contributor.departmentUniversidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticases_ES
dc.contributor.departmentNafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematika Sailaeu
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessen
dc.rights.accessRightsAcceso abierto / Sarbide irekiaes
dc.identifier.doi10.1255/jsi.2020.a16
dc.relation.publisherversionhttps://doi.org/10.1255/jsi.2020.a16
dc.type.versioninfo:eu-repo/semantics/publishedVersionen
dc.type.versionVersión publicada / Argitaratu den bertsioaes


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

© 2020 The Authors. This work is licensed under a Creative Commons BY-NC-ND Licence.
Except where otherwise noted, this item's license is described as © 2020 The Authors. This work is licensed under a Creative Commons BY-NC-ND Licence.