To Örebro University

oru.seÖrebro universitets publikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Neural network approach for shape-based euhedral pyrite identification in X-ray CT data with adversarial unsupervised domain adaptation
Örebro universitet, Institutionen för naturvetenskap och teknik. (MPI Lab (AASS))ORCID-id: 0000-0003-0901-5973
Orexplore AB, Kista, Stockholm, Sweden.
Orexplore AB, Kista, Stockholm, Sweden.
Örebro universitet, Institutionen för naturvetenskap och teknik. (Center for Applied Autonomous Sensor Systems (AASS))ORCID-id: 0000-0002-0579-7181
Vise andre og tillknytning
2024 (engelsk)Inngår i: Applied Computing and Geosciences, E-ISSN 2590-1974, Vol. 21, artikkel-id 100153Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

We explore an attenuation and shape-based identification of euhedral pyrites in high-resolution X-ray Computed Tomography (XCT) data using deep neural networks. To deal with the scarcity of annotated data we generate a complementary training set of synthetic images. To investigate and address the domain gap between the synthetic and XCT data, several deep learning models, with and without domain adaption, are trained and compared. We find that a model trained on a small set of human annotations, while displaying over-fitting, can rival the human annotators. The unsupervised domain adaptation approaches are successful in bridging the domain gap, which significantly improves their performance. A domain-adapted model, trained on a dataset that fuses synthetic and real data, is the overall best-performing model. This highlights the possibility of using synthetic datasets for the application of deep learning in mineralogy.

sted, utgiver, år, opplag, sider
Elsevier, 2024. Vol. 21, artikkel-id 100153
Emneord [en]
Mineral identification, Unsupervised domain adaptation, Deep convolutional neural network, Semantic segmentation, Euhedral pyrites
HSV kategori
Forskningsprogram
Datavetenskap
Identifikatorer
URN: urn:nbn:se:oru:diva-111189DOI: 10.1016/j.acags.2023.100153ISI: 001155327400001Scopus ID: 2-s2.0-85182272087OAI: oai:DiVA.org:oru-111189DiVA, id: diva2:1832249
Forskningsfinansiär
Knowledge Foundation, 20190128
Merknad

This work has been supported by the Industrial Graduate School Collaborative AI and Robotics funded by the Swedish Knowledge Foundation Dnr:20190128 and in collaboration with the industrial partner Orexplore Technologies.

Tilgjengelig fra: 2024-01-29 Laget: 2024-01-29 Sist oppdatert: 2024-02-14bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Neelakantan, SurajLängkvist, MartinLoutfi, Amy

Søk i DiVA

Av forfatter/redaktør
Neelakantan, SurajLängkvist, MartinLoutfi, Amy
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 32 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf