A signal/semantic framework for image retrieval

Author

Mulhem, Philippe ; Chiaramella, Yves ; Belkhatir, Mohammed

Author_Institution

MRIM-IMAG/CNRS

fYear

2005

fDate

7-11 June 2005

Firstpage

368

Lastpage

368

Abstract

The article presents an approach for integrating perceptual signal features (i.e. color and texture) and semantic information within an integrated architecture for image retrieval. It relies on an expressive knowledge representation formalism handling high-level image descriptions and a full-text query framework. It consequently brings the level of image retrieval closer to users´ needs by translating low-level signal features to high-level data and coupling it with semantics within index and query structures

Keywords

full-text databases; image retrieval; knowledge representation; expressive knowledge representation formalism; full-text query framework; high-level data; high-level image descriptions; image retrieval; integrated architecture; low-level signal features; perceptual signal features; query structures; semantic information; signal/semantic integration; Character generation; Color; Content based retrieval; Image retrieval; Indexing; Information retrieval; Knowledge representation; Labeling; Lattices; Organizing; image retrieval; signal/semantic integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Libraries, 2005. JCDL '05. Proceedings of the 5th ACM/IEEE-CS Joint Conference on

Conference_Location

Denver, CO

Print_ISBN

1-58113-876-8

Type

conf

DOI

10.1145/1065385.1065471

Filename

4118571