Wo introduce a new content-based image retrieval system, named ImageRoadMap, for retrieval by visual information. ImageRoadMap provides both computer vision capabilities and database lruimigement capabilities. We describe the architectural design of the system and its six main components: Image Processing Object, Image Database Object, Domain Management Object, Feature Extraction Object,Visual Query Object, and Data Retrieval and Indexing Object. These objects are independent of one another and may be replaced by objects with equivalent or enhanced features. The Image Database Object is responsible for management of actual image data, visual features and other data types. It performs similarity measurement and similarity based indexing. By utilizing Self-Organizing Feature Map (SOFM) and other indexing methods, spatial color distribution, dominant color set, number of objects and other visual features may be computed. Users of ImageRoadMap may present queries in several different ways depending on the characteristics and the nature of the query. Currently the system supports: Query by Example, Query by Color Contents, Query by Sketch, and Query by Concept.
展开▼
