Show simple item record

Plant disease detections using deep learning techniques

dc.contributor.advisorSladojević, Srđan
dc.contributor.otherStefanović, Darko
dc.contributor.otherAnderla, Andraš
dc.contributor.otherIvanišević, Dragoslav
dc.contributor.otherRakić, Aleksandar
dc.contributor.otherSladojević, Srđan
dc.creatorArsenović, Marko
dc.date.accessioned2021-02-25T14:53:29Z
dc.date.available2021-02-25T14:53:29Z
dc.date.issued2020-10-07
dc.identifier.urihttps://www.cris.uns.ac.rs/DownloadFileServlet/Disertacija159437067647076.pdf?controlNumber=(BISIS)114816&fileName=159437067647076.pdf&id=16035&source=NaRDuS&language=srsr
dc.identifier.urihttps://www.cris.uns.ac.rs/record.jsf?recordId=114816&source=NaRDuS&language=srsr
dc.identifier.urihttps://www.cris.uns.ac.rs/DownloadFileServlet/IzvestajKomisije159437068315281.pdf?controlNumber=(BISIS)114816&fileName=159437068315281.pdf&id=16036&source=NaRDuS&language=srsr
dc.identifier.uri/DownloadFileServlet/IzvestajKomisije159437068315281.pdf?controlNumber=(BISIS)114816&fileName=159437068315281.pdf&id=16036
dc.identifier.urihttps://nardus.mpn.gov.rs/handle/123456789/17974
dc.description.abstractIstraživanja predstavljena u disertaciji imala su za cilj razvoj nove metode bazirane na dubokim konvolucijskim neuoronskim mrežama u cilju detekcije bolesti biljaka na osnovu slike lista. U okviru eksperimentalnog dela rada prikazani su dosadašnji literaturno dostupni pristupi u automatskoj detekciji bolesti biljaka kao i ograničenja ovako dobijenih modela kada se koriste u prirodnim uslovima. U okviru disertacije uvedena je nova baza slika listova, trenutno najveća po broju slika u poređenju sa javno dostupnim bazama, potvrđeni su novi pristupi augmentacije bazirani na GAN arhitekturi nad slikama listova uz novi specijalizovani dvo-koračni pristup kao potencijalni odgovor na nedostatke postojećih rešenja.sr
dc.description.abstractThe research presented in this thesis was aimed at developing a novel method based on deep convolutional neural networks for automated plant disease detection. Based on current available literature, specialized two-phased deep neural network method introduced in the experimental part of thesis solves the limitations of state-of-the-art plant disease detection methods and provides the possibility for a practical usage of the newly developed model. In addition, a new dataset was introduced, that has more images of leaves than other publicly available datasets, also GAN based augmentation approach on leaves images is experimentally confirmed.en
dc.languagesr (latin script)
dc.publisherУниверзитет у Новом Саду, Факултет техничких наукаsr
dc.rightsopenAccessen
dc.sourceУниверзитет у Новом Садуsr
dc.subjectDuboko učenje, konovolucijske neuronske mreže, klasifikacija, detekcija objekatasr
dc.subjectDeep learning, convolutional neural networks, classification, object detectionen
dc.titleDetekcija bolesti biljaka tehnikama dubokog učenjasr
dc.title.alternativePlant disease detections using deep learning techniquesen
dc.typedoctoralThesisen
dc.rights.licenseBY-NC
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/68730/Disertacija.pdf
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/68732/IzvestajKomisije.pdf


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record