Presentation 1994/10/21
Similarity Retrieval of Satellite Cloud Imagery Based on Optimization Principle
Asanobu Kitamoto, Mikio Takagi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Similarity retrieval technology,which,from image databases, enables users to retrieve images that have similar contents to the retrieval key,becomes an essential technology as image databases grows to very large ones.This paper deals with cloud in satellite imagery,and builds a similarity retrieval system based on the similarities of shape and spatial distribution of cloud regions. First the shape of a cloud region is represented using shape decomposition by affine-related polygons;then the decomposition result is structured into an attributed relational graph.This formulation naturally defines the similarity measure as graph matching cost.Moreover,the system tries to learn human subjective evaluation by adjusting weighting factors associated with graph matching cost.All the methods are formulated based on optimization principle.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Similarity retrieval / optimization priciple / shape decomposition / attributed relational groph / subjective evaluation / satellite cloud imagery
Paper # PRU94-49
Date of Issue

Conference Information
Committee PRU
Conference Date 1994/10/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Understanding (PRU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Similarity Retrieval of Satellite Cloud Imagery Based on Optimization Principle
Sub Title (in English)
Keyword(1) Similarity retrieval
Keyword(2) optimization priciple
Keyword(3) shape decomposition
Keyword(4) attributed relational groph
Keyword(5) subjective evaluation
Keyword(6) satellite cloud imagery
1st Author's Name Asanobu Kitamoto
1st Author's Affiliation Institute of Industrial Science,University of Tokyo()
2nd Author's Name Mikio Takagi
2nd Author's Affiliation Institute of Industrial Science,University of Tokyo
Date 1994/10/21
Paper # PRU94-49
Volume (vol) vol.94
Number (no) 294
Page pp.pp.-
#Pages 8
Date of Issue