Towards a semantic image database system

Abstract

A semantic image database system (OISDBS) has been designed for structural management of image data. A semantic image data model has been presented to describe the inner structure and contents of images. A diagrammatic query language with a QBE (Query-by-example) flavor is proposed together with a discussion of its foundation on object rewriting. This data model describes the structure and contents of images by incorporating type constructors, functions on types, and inheritance. It supports composite modeling for entities which consist of pictorial data as well as alphanumeric attributes. The interactive query language allows users to do direct manipulation on the pictorial database because such diagrammatic query formulations represent the users' view of the database schema. Various aspects of OISDBS such as the schema design, storage management, and mapping from semantic schema to relational schema, are also discussed.