Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorPicek, Lukáš
dc.contributor.authorŠulc, Milan
dc.contributor.authorMatas, Jiří
dc.contributor.authorHeilmann-Clausen, Jacob
dc.contributor.authorJeppesen, Thomas S.
dc.contributor.authorLind, Emil
dc.date.accessioned2023-01-30T11:00:28Z-
dc.date.available2023-01-30T11:00:28Z-
dc.date.issued2022
dc.identifier.citationPICEK, L. ŠULC, M. MATAS, J. HEILMANN-CLAUSEN, J. JEPPESEN, TS. LIND, E. Automatic Fungi Recognition: Deep Learning Meets Mycology. SENSORS, 2022, roč. 22, č. 2, s. 1-22. ISSN: 1424-8220cs
dc.identifier.issn1424-8220
dc.identifier.uri2-s2.0-85122898591
dc.identifier.urihttp://hdl.handle.net/11025/51169
dc.format22 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherMDPIen
dc.relation.ispartofseriesSENSORSen
dc.rights© authorsen
dc.titleAutomatic Fungi Recognition: Deep Learning Meets Mycologyen
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThe article presents an AI-based fungi species recognition system for a citizen-science community. The system’s real-time identification too — FungiVision — with a mobile application front-end, led to increased public interest in fungi, quadrupling the number of citizens collecting data. FungiVision, deployed with a human-in-the-loop, reaches nearly 93% accuracy. Using the collected data, we developed a novel fine-grained classification dataset — Danish Fungi 2020 (DF20) — with several unique characteristics: species-level labels, a small number of errors, and rich observation metadata. The dataset enables the testing of the ability to improve classification using metadata, e.g., time, location, habitat and substrate, facilitates classifier calibration testing and finally allows the study of the impact of the device settings on the classification performance. The continual flow of labelled data supports improvements of the online recognition system. Finally, we present a novel method for the fungi recognition service, based on a Vision Transformer architecture. Trained on DF20 and exploiting available metadata, it achieves a recognition error that is 46.75% lower than the current system. By providing a stream of labeled data in one direction, and an accuracy increase in the other, the collaboration creates a virtuous cycle helping both communities.en
dc.subject.translatedArtificial intelligenceen
dc.subject.translatedClassificationen
dc.subject.translatedComputer visionen
dc.subject.translatedFine-graineden
dc.subject.translatedFungien
dc.subject.translatedMachine learningen
dc.subject.translatedRecognitionen
dc.subject.translatedSpeciesen
dc.subject.translatedSpecies recognitionen
dc.identifier.doi10.3390/s22020633
dc.type.statusPeer-revieweden
dc.identifier.document-number746955100001
dc.identifier.obd43937003
dc.project.IDSGS-2019-027/Inteligentní metody strojového vnímání a porozumění 4cs
dc.project.IDLM2018101/LINDAT/CLARIAH-CZ – Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědycs
dc.project.IDLO1506/PUNTIS - Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnostcs
Vyskytuje se v kolekcích:Články / Articles (NTIS)
Články / Articles (KKY)
OBD

Soubory připojené k záznamu:
Soubor VelikostFormát 
Picek_et_al_Automatic_Fungi_Recognition_Sensors_2022.pdf15,37 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/51169

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. OBD