Content-adaptive pyramid representation for 3D object classification

Tsampikos Kounalakis, Nikolaos Boulgouris, Georgios Triantafyllidis

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

2 Citationer (Scopus)

Abstrakt

In this paper we introduce a novel representation for the classification of 3D images. Unlike most current approaches, our representation is not based on a fixed pyramid but adapts to image content and uses image regions instead of rectangular pyramid scales. Image characteristics, such as depth and color, are used for defining regions within images. Multiple region scales are formed in order to construct the proposed pyramid image representation. The proposed method achieves excellent results in comparison to conventional representations.
OriginalsprogEngelsk
TitelIEEE International Conference on Image Processing (ICIP), 2016
Antal sider4
ForlagIEEE
Publikationsdato28 sep. 2016
Sider231-235
ISBN (Trykt)978-1-4673-9962-3
ISBN (Elektronisk)978-1-4673-9961-6
DOI
StatusUdgivet - 28 sep. 2016
BegivenhedIEEE International Conference on Image Processing - Arizona, Phoenix, USA
Varighed: 25 sep. 201628 sep. 2016
http://2016.ieeeicip.org/

Konference

KonferenceIEEE International Conference on Image Processing
LokationArizona
LandUSA
ByPhoenix
Periode25/09/201628/09/2016
Internetadresse

Fingeraftryk Dyk ned i forskningsemnerne om 'Content-adaptive pyramid representation for 3D object classification'. Sammen danner de et unikt fingeraftryk.

Citationsformater