3D model-based still image object categorization

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

Abstract

This paper proposes a novel recognition scheme algorithm for semantic labeling of 2D object present in still images. The principle consists of matching unknown 2D objects with categorized 3D models in order to infer 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. Results obtained show promising performances, with recognition rate up to 84%, which opens interesting perspectives in terms of semantic metadata extraction from still images/videos.

Original languageEnglish
Title of host publicationMathematics of Data/Image Pattern Coding, Compression, and Encryption with Applications XIII
DOIs
Publication statusPublished - 1 Dec 2011
EventMathematics of Data/Image Pattern Coding, Compression, and Encryption with Applications XIII - San Diego, CA, United States
Duration: 21 Aug 201124 Aug 2011

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8136
ISSN (Print)0277-786X

Conference

ConferenceMathematics of Data/Image Pattern Coding, Compression, and Encryption with Applications XIII
Country/TerritoryUnited States
CitySan Diego, CA
Period21/08/1124/08/11

Keywords

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

Fingerprint

Dive into the research topics of '3D model-based still image object categorization'. Together they form a unique fingerprint.

Cite this