Presentation 1999/7/15
Image understanding using dividing and vector quantization of images with multiple words
Yasuhide MORI, Hironobu TAKAHASHI, Ryuichi OKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We developed an image-word correlating method using dividing images with key words and vector quantization of features. The original points of the method are, (1) all words assigned to a whole image are inherited to each divided part of image, (2) voting probability of each word in a set of divided images is estimated by the result of vector quantization of their feature vector. Experiments show the effectiveness of dividing and vector quantization in the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrieval / image understanding / vector quantization / key words / image dividing, Bayes estimation
Paper # MVE99-43
Date of Issue

Conference Information
Committee MVE
Conference Date 1999/7/15(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image understanding using dividing and vector quantization of images with multiple words
Sub Title (in English)
Keyword(1) image retrieval
Keyword(2) image understanding
Keyword(3) vector quantization
Keyword(4) key words
Keyword(5) image dividing, Bayes estimation
1st Author's Name Yasuhide MORI
1st Author's Affiliation Real World Computing Partnership Information Basis Function Laboratory()
2nd Author's Name Hironobu TAKAHASHI
2nd Author's Affiliation Real World Computing Partnership Information Basis Function Laboratory
3rd Author's Name Ryuichi OKA
3rd Author's Affiliation Real World Computing Partnership Information Basis Function Laboratory
Date 1999/7/15
Paper # MVE99-43
Volume (vol) vol.99
Number (no) 183
Page pp.pp.-
#Pages 8
Date of Issue