Text-Based Image Retrieval Using Earth Mover's Distance
Language
Japanese
Type
Proceedings of Japanese Conferences
Authors
Kinji Takeuchi, Koichi Kise
Title
Text-Based Image Retrieval Using Earth Mover's Distance
Journal
情報処理学会研究報告
No.
NL-177-5
Reviewed
Not reviewed
Date
January 2007
Research fields
Information Retrieval
Key
Takeuchi2007_SIG (id=962)
Abstract
In this report, we propose a method of Text-Based Image Retrieval(TBIR) using Earth Mover's Distance(EMD).
Our approach uses EMD to combine textual and visual features into one semantic space,
to improve the performance of TBIR.
We compare our method with four conventional methods including LSI and PLSI.
The results show our method is superior to others in average precision.
We also applied an approximation in computing EMD for improving the efficiency of the proposed method.
The results show that the approximate method can reduce the computational complexity in about 8%,
with little loss of average precision.
Files
…
Export this publication
Tab-separated. Paste into the sheet starting at column A. Required fields that cannot be inferred are left blank.
Format definition
Edits apply immediately and stay in effect until you pick a style again or reset. First line is the default; add lines like "book: …" to override per type.
How to write the definition
Insert a field with braces like {authors}. A part enclosed in [ ... ] is omitted entirely when any field inside it is empty. Available fields:
One macro per line as \name{field}{field}…. A field name in braces is replaced by its (LaTeX-escaped) value; other text is kept. Rename macros or add lines freely — they appear in the macro selector. A line like master_thesis: thesis fixes the macro for a type (automatic choice: journals use paperdoi with a DOI, paperno with a number, else paper; conferences conf with pages, else confpaper; books book). {pages} comes as 119--124; {journal} falls back to the book title. Fields: