Query Processing on Image Databases

This paper describes the retrieval process from image databases, based on a description of the image content. This process is based on the assumption that a semantic interpretation of the image content is available, as result of an automatic, or semi-automatic, image analysis process, applied to images belonging to specific domains, described in advance to the system. The result of the analysis process on an image, called Image Symbolic Representation at Database Level, contains the description of the basic and complex objects, recognized in the image, with different interpretations and different levels of recognition. The user sees the images at another level which is simpler than the database level (Image Symbolic Representation at End-User Level). Therefore, the user will formulate queries on these semantic image interpretations. The image query language allows the user to express conditions on the symbolic representation of the images to be retrieved. It addresses the important aspects of the various image interpretations, like partial conditions on the composition of the complex objects in the image, their degree of recognition. and positional requirements on the objects in the image interpretation. The paper describes the processing of queries expressed using the image query language, discussing also the access structures to support fast content-base image retrieval.