Figure1. Image retrieval architecture based on conventional database.
Figure 2. Model for image object.
Figure 3. Architecture of the database. It is composed by an CGI, Query
interpreter, Image analyzer, OO-Database, User View (UV).
Figure 4. When accessing to database content two users has to be allowed
to recover data according to their specialty.
Figure 5. Query processor. The query is processed as follows: 1. A user
require a service to the system; 2. a software agent is built according
to the adopted retrieval method and user skills; 3. the proper query operators
are chosen; 4. a custom model of the image is also built according to user
specialty; 5. agent processes the query; 6. the coded result is sent to
the interface to database block; 7. mapping function recovers into the
database a set relevant image; 8. between this set, a degree of relevance
to the user query is then computed; 9. filtering function identifies primitive
features to retrieve in the image according to image model.
