2005 | OriginalPaper | Buchkapitel
A Full-Text Framework for the Image Retrieval Signal/Semantic Integration
verfasst von : Mohammed Belkhatir, Philippe Mulhem, Yves Chiaramella
Erschienen in: Database and Expert Systems Applications
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper presents an approach for integrating perceptual signal features (i.e. color and texture) and semantic information within a coupled architecture for image indexing and 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 conceptual data and integrate them with semantic characterization within index and query structures. Experiments on a corpus of 2500 photographs validate our approach by considering recall-precision indicators over a set of 46 full-text queries coupling high-level semantic and signal features.