Content-adaptive pyramid representation for 3D object classification

Tsampikos Kounalakis, Nikolaos Boulgouris, Georgios Triantafyllidis

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

2 Citations (Scopus)

Abstract

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.
Original languageEnglish
Title of host publicationIEEE International Conference on Image Processing (ICIP), 2016
Number of pages4
PublisherIEEE
Publication date28 Sep 2016
Pages231-235
ISBN (Print)978-1-4673-9962-3
ISBN (Electronic)978-1-4673-9961-6
DOIs
Publication statusPublished - 28 Sep 2016
EventIEEE International Conference on Image Processing - Arizona, Phoenix, United States
Duration: 25 Sep 201628 Sep 2016
http://2016.ieeeicip.org/

Conference

ConferenceIEEE International Conference on Image Processing
LocationArizona
CountryUnited States
CityPhoenix
Period25/09/201628/09/2016
Internet address

Fingerprint

Color

Cite this

Kounalakis, T., Boulgouris, N., & Triantafyllidis, G. (2016). Content-adaptive pyramid representation for 3D object classification. In IEEE International Conference on Image Processing (ICIP), 2016 (pp. 231-235). IEEE. https://doi.org/10.1109/ICIP.2016.7532353
Kounalakis, Tsampikos ; Boulgouris, Nikolaos ; Triantafyllidis, Georgios. / Content-adaptive pyramid representation for 3D object classification. IEEE International Conference on Image Processing (ICIP), 2016. IEEE, 2016. pp. 231-235
@inproceedings{626bc6c24d5a482cb69a4a38a2e84c33,
title = "Content-adaptive pyramid representation for 3D object classification",
abstract = "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.",
author = "Tsampikos Kounalakis and Nikolaos Boulgouris and Georgios Triantafyllidis",
year = "2016",
month = "9",
day = "28",
doi = "10.1109/ICIP.2016.7532353",
language = "English",
isbn = "978-1-4673-9962-3",
pages = "231--235",
booktitle = "IEEE International Conference on Image Processing (ICIP), 2016",
publisher = "IEEE",
address = "United States",

}

Kounalakis, T, Boulgouris, N & Triantafyllidis, G 2016, Content-adaptive pyramid representation for 3D object classification. in IEEE International Conference on Image Processing (ICIP), 2016. IEEE, pp. 231-235, IEEE International Conference on Image Processing , Phoenix, United States, 25/09/2016. https://doi.org/10.1109/ICIP.2016.7532353

Content-adaptive pyramid representation for 3D object classification. / Kounalakis, Tsampikos; Boulgouris, Nikolaos; Triantafyllidis, Georgios.

IEEE International Conference on Image Processing (ICIP), 2016. IEEE, 2016. p. 231-235.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Content-adaptive pyramid representation for 3D object classification

AU - Kounalakis, Tsampikos

AU - Boulgouris, Nikolaos

AU - Triantafyllidis, Georgios

PY - 2016/9/28

Y1 - 2016/9/28

N2 - 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.

AB - 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.

UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7532353&isnumber=7532277

U2 - 10.1109/ICIP.2016.7532353

DO - 10.1109/ICIP.2016.7532353

M3 - Article in proceeding

SN - 978-1-4673-9962-3

SP - 231

EP - 235

BT - IEEE International Conference on Image Processing (ICIP), 2016

PB - IEEE

ER -

Kounalakis T, Boulgouris N, Triantafyllidis G. Content-adaptive pyramid representation for 3D object classification. In IEEE International Conference on Image Processing (ICIP), 2016. IEEE. 2016. p. 231-235 https://doi.org/10.1109/ICIP.2016.7532353