Presentation 2001/3/16
Image Retrieval with Multi-Stage Filtering in Low Dimensions
Kohei INOUE, Kiichi URAHAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) An acceleration method is examined for kNN search of color images on the basis of transformation of quadratic form distances into their canonical forms. Basic filtering method and its improved version are extended to two-stage filtering. It is shown by experiments that this extension reduces computational time for kNN image retrieval. Three feature vectors of images are examined, one is popular color histograms, next is block partitioned histograms and final is pixel color histograms. Latter feature vectors include more detailed information of spatial structure in images and are shown by experiments to be capable to differentiate color structure in images more precisely.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrieval / similarity search / filtering / dimensionality reduction
Paper # PRMU2000-238
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/3/16(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 Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Retrieval with Multi-Stage Filtering in Low Dimensions
Sub Title (in English)
Keyword(1) image retrieval
Keyword(2) similarity search
Keyword(3) filtering
Keyword(4) dimensionality reduction
1st Author's Name Kohei INOUE
1st Author's Affiliation Faculty of Visual Communication Design, Kyushu Institute of Design()
2nd Author's Name Kiichi URAHAMA
2nd Author's Affiliation Faculty of Visual Communication Design, Kyushu Institute of Design
Date 2001/3/16
Paper # PRMU2000-238
Volume (vol) vol.100
Number (no) 702
Page pp.pp.-
#Pages 6
Date of Issue