Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikačního výsledku
UHER, V.; BURGET, R.; KARÁSEK, J.; MAŠEK, J.; DUTTA, M.
Originální název
Automatic Image Labelling using Similarity Measures
Anglický název
Druh
Stať ve sborníku v databázi WoS či Scopus
Originální abstrakt
Scene classification based on global features. It can be used, for example, for annotating large databases of photos. The whole process has several steps. The first step is features extraction, and then the distance between a new image and reference images is calculated. A model is trained to classify new images based on this distance. The model was created using the Naïve Bayes classifier. To improve accuracy the forward selection was used, which optimizes the selection of a group of attributes. The overall performance on the testing dataset was 69.76%.
Anglický abstrakt
Klíčová slova
Scene classification; image labelling; machine learning; image processing
Klíčová slova v angličtině
Autoři
Rok RIV
2015
Vydáno
12.01.2015
Nakladatel
IEEE
Místo
Greater Noida
ISBN
978-1-4799-5096-6
Kniha
MEDCOM 2014 CD-ROM
Strany od
101
Strany do
104
Strany počet
4
URL
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7005984&refinements%3D4273474444%26sortType%3Dasc_p_Sequence%26filter%3DAND%28p_IS_Number%3A7005558%29
BibTex
@inproceedings{BUT109408, author="Václav {Uher} and Radim {Burget} and Jan {Karásek} and Jan {Mašek} and Malay Kishore {Dutta}", title="Automatic Image Labelling using Similarity Measures", booktitle="MEDCOM 2014 CD-ROM", year="2015", pages="101--104", publisher="IEEE", address="Greater Noida", doi="10.1109/MedCom.2014.7005984", isbn="978-1-4799-5096-6", url="http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7005984&refinements%3D4273474444%26sortType%3Dasc_p_Sequence%26filter%3DAND%28p_IS_Number%3A7005558%29" }