Context-sensitive processing of semantic queries in an image database system
Information Processing and Management: an International Journal - Special issue: history of information science
Towards a semantic image database system
Data & Knowledge Engineering
Modeling and retrieving images by content
Information Processing and Management: an International Journal
Visual information retrieval from large distributed online repositories
Communications of the ACM
Managing multimedia information in database systems
Communications of the ACM
Attributes of images in describing tasks
Information Processing and Management: an International Journal
Hierarchical image modeling for object-based media retrieval
Data & Knowledge Engineering
Similarity Retrieval of Trademark Images
IEEE MultiMedia
Image Data Modeling for Efficient Content Indexing
IW-MMDBMS '95 Proceedings of the International Workshop on Multi-Media Database Management Systems
Hi-index | 0.00 |
Search effectiveness in an image database is always a trade-off between the indexing cost and semantic richness. A solution that provides a significant degree of semantic richness that simultaneously limits the indexing cost is presented. The query schemes are able to enhance the query speed by adopting a semantically rich structured form for high-level image content information, as well as exploiting the efficiency of conventional database search. Through the use of rules, which can be either pre-defined or dynamically incorporated a new level of semantic richness can be established, which will eliminate the costly detailed indexing of individual concepts. The query algorithm incorporates rule-based conceptual navigation, customized weighting, incremental indexing and relevance feedback mechanisms to enhance retrieval effectiveness.