The unification of keywords and feature contents for image retrieval is addressed. A seamless joint querying and relevance feedback scheme based on both keywords and low-level visual contents incorporating keyword similarities is proposed. An algorithm for the learning of the word similarity matrix during user interaction is introduced. This learned similarity matrix can be applied for keyword semantic grouping, thesaurus construction, and soft query expansion during intelligent image retrieval.
ASJC Scopus subject areas
- Signal Processing
- Media Technology
- Hardware and Architecture
- Computer Science Applications