DocumentCode
2061249
Title
Sill Image Object Categorization Using 2D Objects Models
Author
Petre, Raluca-Diana ; Zaharia, Titus
Author_Institution
ARTEMIS Dept., TELECOM SudParis, Evry, France
fYear
2011
fDate
18-21 Sept. 2011
Firstpage
419
Lastpage
423
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%.
Keywords
image matching; image retrieval; object recognition; video coding; 2D object matching; 2D object model; MPEG-7; Princeton 3D model database; recognition scheme; semantic labeling; still image object categorization; Indexing; Object recognition; Shape; Solid modeling; Three dimensional displays; Transform coding; 2D and 3D shape descriptors; 2D/3D indexing; indexing and retrieval; object classification;
fLanguage
English
Publisher
ieee
Conference_Titel
Semantic Computing (ICSC), 2011 Fifth IEEE International Conference on
Conference_Location
Palo Alto, CA
Print_ISBN
978-1-4577-1648-5
Electronic_ISBN
978-0-7695-4492-2
Type
conf
DOI
10.1109/ICSC.2011.22
Filename
6061470
Link To Document