Object classification with artificial neural networks: A comparative analysis

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Niewiadomski, Artur
dc.contributor.author Domeradzki, Kornel
dc.date.accessioned 2021-04-27T08:34:54Z
dc.date.available 2021-04-27T08:34:54Z
dc.date.issued 2019
dc.identifier.citation Studia Informatica : systemy i technologie informacyjne. Nr 23 (2019), s. 43-56 pl
dc.identifier.issn 1731-2264
dc.identifier.uri http://hdl.handle.net/11331/3491
dc.description.abstract Object classification is a problem which has attracted a lot of research attention in recent years. Traditional approach to this problem is built on a shallow trainable architecture that was meant to detect handcrafted features. That approach works poorly and introduces many complications in situations where one is to work with more than a couple types of objects in an image with a large resolution. That is why in the past few years convolutional and residual neural networks have experienced a tremendous rise in popularity. In this paper, we provide a review on topics related to artificial neural networks and a brief overview of our research. Our review begins with a short introduction to the topic of computer vision. Afterwards we cover briefly the concepts of neural networks, convolutional and residual neural networks and their commonly used models. Then we provide a comparative performance analysis of the previously mentioned models in a binary and multi-label classification problem. Finally, multiple conclusions are drawn, which are to serve as guidelines for future computer vision systems implementations. pl
dc.language.iso en pl
dc.publisher Wydawnictwo Uniwersytetu Przyrodniczo-Humanistycznego pl
dc.rights Uznanie autorstwa-Na tych samych warunkach 3.0 Polska *
dc.rights.uri http://creativecommons.org/licenses/by-sa/3.0/pl/ *
dc.subject Image recognition pl
dc.subject Neural networks pl
dc.subject Rozpoznawanie obrazów pl
dc.subject Sieci neuronowe pl
dc.title Object classification with artificial neural networks: A comparative analysis pl
dc.type Article pl


Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Uznanie autorstwa-Na tych samych warunkach 3.0 Polska Except where otherwise noted, this item's license is described as Uznanie autorstwa-Na tych samych warunkach 3.0 Polska

Search DSpace


Advanced Search

Browse

My Account

Statistics