Sill image object categorization using 2D models

Raluca Diana Petre, Titus Zaharia

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a novel recognition scheme for semantic labeling of 2D objects present in still images. The principle consists of matching unknown 2D objects with categorized 3D models in order to associate the semantics of the 3D object to the image. We tested our new recognition framework by using the MPEG-7 and Princeton 3D model databases in order to label unknown images randomly selected from the web. Experiments show that such a system can achieve recognition rate up to 70.4%.

Original languageEnglish
Title of host publicationProceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011
Pages419-423
Number of pages5
DOIs
Publication statusPublished - 21 Nov 2011
Externally publishedYes
Event5th Annual IEEE International Conference on Semantic Computing, ICSC 2011 - Palo Alto, CA, United States
Duration: 18 Sept 201121 Sept 2011

Publication series

NameProceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011

Conference

Conference5th Annual IEEE International Conference on Semantic Computing, ICSC 2011
Country/TerritoryUnited States
CityPalo Alto, CA
Period18/09/1121/09/11

Keywords

  • 2D and 3D shape descriptors
  • 2D/3D indexing
  • Indexing and retrieval
  • Object classification

Fingerprint

Dive into the research topics of 'Sill image object categorization using 2D models'. Together they form a unique fingerprint.

Cite this