Paper Info
Title
A Classification Method of Images Based on Composition and Its Application to Image Retrieval
Abstract
We propose a visual query method for image retrieval, in which the user expresses the composition of the target image by selecting one of the composition types presented by the system, and also propose an image classification method to derive composition types from an image database. From the viewpoint of communication between the system and its user, we point out the problem of visual query methods using concrete images as queries. Though suited to convey visual image properties, they grow the ambiguity in the system's interpretation of queries. To manage this tradeoff, we implemented our methods in a prototype system and derived composition types from an image database to show how our query method works in image retrieval.
Year
DOI
Venue
1999
10.1109/MMCS.1999.778300
ICMCS, Vol. 1
Keywords
Field
DocType
visual query method,target image,image classification method,image database,prototype system,image retrieval,visual image property,composition type,concrete image,query method work,classification method,image classification,image resolution,information retrieval,prototypes,informatics,human interface,concrete
Computer vision,Automatic image annotation,Feature detection (computer vision),Image texture,Computer science,Image retrieval,Image processing,Artificial intelligence,Contextual image classification,Image resolution,Visual Word
Conference
ISBN
Citations 
PageRank 
0-7695-0253-9
0
0.34
References 
Authors
3
3
Name
Order
Citations
PageRank
Shigenori Maeda101.01
Masayuki Mukunoki219921.86
Katsuo Ikeda38433.77