Presentation 2011-03-28
Subregion Retrieval of Natural Images by Using Tree Structures, and Application to Fractal Compression and Image Mining
Takashi FUKUMURA, Mahito SUGIYAMA, Akihiro YAMAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new method for speeding up retrieval of subregions in natural images by using tree structures. We evaluate our method by fractal compression, and moreover we apply the method to image mining. In our method a tree called an index tree is generated from given subregions by using bit planes. Our experiments show that faster fractal compression is achieved by using index trees. As the application of our method to image mining, we treat the problem of extracting frequent subregions as features of an image. As a solution, we propose a new method to find sets of frequent paths from sets of index trees. We give some experimental results showing that we can regard the number of frequent subregions as features of an image. We also found same images whose waveform cannot be regarded as features.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Retrieval / Tree Structure / Data Mining / Fractal
Paper # IBISML2010-112
Date of Issue

Conference Information
Committee IBISML
Conference Date 2011/3/21(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Subregion Retrieval of Natural Images by Using Tree Structures, and Application to Fractal Compression and Image Mining
Sub Title (in English)
Keyword(1) Retrieval
Keyword(2) Tree Structure
Keyword(3) Data Mining
Keyword(4) Fractal
1st Author's Name Takashi FUKUMURA
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name Mahito SUGIYAMA
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
3rd Author's Name Akihiro YAMAMOTO
3rd Author's Affiliation Graduate School of Informatics, Kyoto University
Date 2011-03-28
Paper # IBISML2010-112
Volume (vol) vol.110
Number (no) 476
Page pp.pp.-
#Pages 8
Date of Issue