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)


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
Publication date28 Sep 2016
ISBN (Print)978-1-4673-9962-3
ISBN (Electronic)978-1-4673-9961-6
Publication statusPublished - 28 Sep 2016
EventIEEE International Conference on Image Processing - Arizona, Phoenix, United States
Duration: 25 Sep 201628 Sep 2016


ConferenceIEEE International Conference on Image Processing
CountryUnited States
Internet address

Fingerprint Dive into the research topics of 'Content-adaptive pyramid representation for 3D object classification'. Together they form a unique fingerprint.

Cite this