Content-Based Image Modeling and Retrieval
Rajiv Mehrotra · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · 1996
A database system models and manages an abstracted real world (or mini-world) pertinent to the problem at hand in terms of alphanumeric data. The semantic associated with any piece of alphanumeric data is known to or derived by the users of the database. This conventional approach to data modeling and management is not well suited for the effective management of imagery data. In an image database management system, the desired information/semantics associated with the imaged mini-world needs to be automatically (or semi-automatically) extracted and appropriately modeled to facilitate content-based retrieval and manipulation of data. In this article, the key issues in content based image data modeling and retrieval are discussed. A system called MUSEUM is briefly presented to illustrate some of the approaches used to resolve the main challenges of consent-based data modeling and retrieval