DC FieldValueLanguage
dc.contributor.authorĆosović, Marijanaen_US
dc.contributor.authorJanković, Radmilaen_US
dc.date.accessioned2020-06-02T10:02:30Z-
dc.date.available2020-06-02T10:02:30Z-
dc.date.issued2020-03-01-
dc.identifier.isbn978-1-728-14775-8-
dc.description.abstractThe cultural heritage image classification represents one of the most important tasks in the process of digitalization. In this paper, a deep learning neural network was applied in order to classify images of architectural heritage belonging to ten categories, in particular: (i) bell tower, (ii) stained glass, (iii) vault, (iv) column, (v) outer dome, (vi) altar, (vii) apse, (viii) inner dome, (ix) flying buttress, and (x) gargoyle. The Convolutional neural network was used for image classification, with the same architecture applied on two sets of the data: the full dataset consisting of 10 categories as well as dataset with 5 different image categories. The results show that both architectures performed well and obtained accuracy of up to 90%.en_US
dc.publisherIEEEen_US
dc.relation.ispartof2020 19th International Symposium INFOTEH-JAHORINA, INFOTEH 2020 - Proceedingsen_US
dc.subjectcultural heritage | deep neural networks | image classification | machine learningen_US
dc.titleCNN Classification of the Cultural Heritage Imagesen_US
dc.typeConference Paperen_US
dc.relation.conference19th International Symposium INFOTEH-JAHORINA, INFOTEH 2020; East Sarajevo; Bosnia and Herzegovina; 18 March 2020 through 20 March 2020en_US
dc.identifier.doi10.1109/INFOTEH48170.2020.9066300-
dc.identifier.scopus2-s2.0-85084983272-
dc.contributor.affiliationMathematical Institute of the Serbian Academy of Sciences and Arts-
dc.relation.firstpage9066300-
dc.description.rankM33-
item.grantfulltextnone-
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeConference Paper-
crisitem.author.orcid0000-0003-3424-134X-
Show simple item record

SCOPUSTM   
Citations

2
checked on Oct 6, 2022

Page view(s)

36
checked on Oct 5, 2022

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.