Image-to-Word Transformation Based on Dividing and Vector Quantizing Images With Words (1999)
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
author = {Yasuhide Mori Hironobu and Hironobu Takahashi and Ryuichi Oka},
title = {Image-to-Word Transformation Based on Dividing and Vector Quantizing Images With Words},
booktitle = {in Boltzmann machines”, Neural Networks},
year = {1999},
pages = {405409}
}
Bookmarks
OpenURL
Abstract:
: We propose a method to make a relationship between images and words. We adopt two processes in the method, one is a process to uniformly divide each image into sub-images with key words, and the other is a process to carry out vector quantization of the sub-images. These processes lead to results which show that each sub-image can be correlated to a set of words each of which is selected from words assigned to whole images. Original aspects of the method are, (1) all words assigned to a whole image are inherited to each divided sub-image, (2) the voting probability of each word for a set of divided images is estimated by the result of a vector quantization of the feature vector of sub-images. Some experiments show the effectiveness of the proposed method. 1 Introduction To permit complete access to the information available through the WWW, media-independent access methods must be developed. For instance, a method enabling use of an image is needed as a possible query to ret...
Citations
| 1 | D.Lee, D.Petkovic, D.Steele and P.Yanker: "Query by Image and Video Content: The QBIC System – Flickner, Ashley, et al. - 1995 |
| 1 | I.Fukuda and A.Sakakura: "Scene retrieval on an image database of full color paintings – Kurita - 1992 |
| 1 | T.Satou and M.Sakauchi: "A flexible content-based image retrieval system with combined scene description keyword – Ono, Hakaridani - 1996 |
| 1 | M.Nagao: "Image analysis using natural language information extracted from explanation text – Watanabe - 1998 |
