The InterImage system is a knowledge based framework for Automatic Image Interpretation. InterImage is an extension of an earlier project called GeoAIDA developed by the Insitut für Informationsverarbeitung - Leibniz Universität Hannover. The interpretation strategy implemented by the system is based on a knowledge model defined by the user, structured as a semantic network. The nodes of the network represent concepts, classes of image objects expected to be found in a scene. Specialized image processing operators (external from the system's core) can be attached to the system, which controls their execution. The instances of the concepts found by the operators are then judged by the system, based on rules defined by the user.
The InteImage environment will permit the construction of automatic image interpretation systems, through the modeling of the knowledge by the specialist. Some functionalities that the system will provide are:
- Extraction of objects/patterns in images and calculation of spectral, geometric, topological and texture properties;
- Modeling of explicit knowledge based on specialist experience for image interpretation through fuzzy rules, fuzzy sets and a semantic net; and
- Processing and visualization of the results for the image interpretation.
Until now the applications implemented using the system have dealt with Remote Sensing Image Data (Satellite or Aerial Images), but there are no particular restrictions over the type of images that can be processed by the system.
InterImage is part of an International Scientific Cooperation Project leaded by the Catholic University of Rio de Janeiro (PUC-Rio) and the Brazilian National Space Research Institute (INPE). Although the system is already operational, and has been tested in various applications, many improvements have been planned, some of which currently being implemented.