Paper Info
Title
Object-Based Image Retrieval Using Active Nets
Abstract
In this work, extraction of relevant objects from images and their matching for retrieval is proposed. Objects are represented by using a two dimensional deformable structure referred to as active net, capable to adapt to relevant image regions according to chromatic and edge information. In particular, this representation allows a joint description of color, shape and structural information of extracted objects. A similarity measure between active nets is also defined and validated in a set of retrieval experiments on the ETH-80 objects database.
Year
DOI
Venue
2006
10.1109/ICPR.2006.887
ICPR (4)
Keywords
Field
DocType
object-based image retrieval,edge information,active net,relevant object,eth-80 objects database,dimensional deformable structure,relevant image region,structural information,retrieval experiment,similarity measure,joint description,active nets,image retrieval,feature extraction
Computer vision,Chromatic scale,Pattern recognition,Similarity measure,Computer science,Image matching,Image representation,Image retrieval,Feature extraction,Image segmentation,Artificial intelligence,Visual Word
Conference
ISSN
ISBN
Citations 
1051-4651
0-7695-2521-0
2
PageRank 
References 
Authors
0.35
6
4
Name
Order
Citations
PageRank
David Garcya-Perez120.35
Antonio Mosquera272.67
Stefano Berretti388052.33
Alberto Del Bimbo43777420.44