Repository logo
 
Publication

Convolutional neural network-based pure paint pigment identification using hyperspectral images

2022-01-10Conference object Restricted access
Simple item page
dc.contributor.authorChen, Ailin
dc.contributor.authorJesus, Rui
dc.contributor.authorVilarigues
dc.date.accessioned2022-01-17T13:57:21Z
dc.date.available2022-01-17T13:57:21Z
dc.date.issued2022-01-10
dc.description.abstractThis research presents the results of the implementation of deep learning neural networks in the identification of pure pigments of heritage artwork, namely paintings. Our paper applies an inno vative three-branch deep learning model to maximise the correct identification of pure pigments. The model proposed combines the feature maps obtained from hyperspectral images through multi ple convolutional neural networks, and numerical, hyperspectral metric data with respect to a set of reference reflectances. The results obtained exhibit an accurate representation of the pure pre dicted pigments which are confirmed through the use of analytical techniques. The model presented outperformed the compared coun terparts and is deemed to be an important direction, not only in terms of utilisation of hyperspectral data and concrete pigment data in heritage analysis, but also in the application of deep learning in other fields.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationCHEN, Ailin; JESUS, Rui; VILARIGUES, Marcia – Convolutional neural network-based pure paint pigment identification using hyperspectral images. In MMAsia '21: ACM Multimedia Asia. Gold Coast, Australia: Association for Computing Machinery, 2021. Pp. 1-7.pt_PT
dc.identifier.doi10.1145/3469877.3495641pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.21/14157
dc.language.isoengpt_PT
dc.publisherAssociation for Computing Machinerypt_PT
dc.relationUIDB/04516/2020 - NOVA LINCSpt_PT
dc.relationUIDB/00729/2020 - VICARTEpt_PT
dc.relationPD/BD/135223/2017 - FCTpt_PT
dc.relation.publisherversionhttps://dl.acm.org/doi/pdf/10.1145/3469877.3495641pt_PT
dc.subjectHyperspectral imagingpt_PT
dc.subjectDeep learningpt_PT
dc.subjectConvolutional neural networkspt_PT
dc.subjectVisualisationpt_PT
dc.subjectPigment identificationpt_PT
dc.titleConvolutional neural network-based pure paint pigment identification using hyperspectral imagespt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.citation.endPage7pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleMMAsia '21: ACM Multimedia Asiapt_PT
person.familyNameJesus
person.familyNameVilarigues
person.givenNameRui
person.givenNameMárcia
person.identifier2682439
person.identifier.ciencia-id041D-93A6-7412
person.identifier.ciencia-idB417-B4B6-E982
person.identifier.orcid0000-0003-1869-6491
person.identifier.orcid0000-0003-4134-2819
person.identifier.scopus-author-id23012170100
rcaap.rightsclosedAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicationcfde72fc-2907-42d5-9b1e-93ddde41c3bd
relation.isAuthorOfPublication38b84d42-86f5-409d-b4af-63558a08952d
relation.isAuthorOfPublication.latestForDiscoverycfde72fc-2907-42d5-9b1e-93ddde41c3bd

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Convolutional_RJesus.pdf
Size:
2.02 MB
Format:
Adobe Portable Document Format
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Comunicações