Presentation	2001/7/12 Dynamic Indexing and Content-based Search by Video Data Mining Fuminao KIKUCHI, Osamu KONISHI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Image data mining deals with the extraction of implicit knowledge, image relationship, and patterns not explicitly stored in image database. It belongs to the scientific discovery. In this paper, we focus video data(a broadcast of a baseball game)with many image information and describe on the construction of video database that can search patterns like a series of scene or change of scene condition. We apply algorithms which we call co-occurrence rules of data mining. It consists of the combination of Self-Organizing feature's Map and time dependency association rules. The results take time sequence data of events and feature patterns extracted over one game. The video databases have been constructed and can answer to user's questions such that we would find any scene as "the batter of the team of precedence have been hitting".
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	DE2001-87
Date of Issue

Conference Information
Committee	DE
Conference Date	2001/7/12(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	Data Engineering (DE)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Dynamic Indexing and Content-based Search by Video Data Mining
Sub Title (in English)
Keyword(1)
1st Author's Name	Fuminao KIKUCHI
1st Author's Affiliation	Dept.of Information Science, Faculty of Science, Kochi Univ.()
2nd Author's Name	Osamu KONISHI
2nd Author's Affiliation	Dept.of Information Science, Faculty of Science, Kochi Univ.
Date	2001/7/12
Paper #	DE2001-87
Volume (vol)	vol.101
Number (no)	193
Page	pp.pp.-
#Pages	8
Date of Issue