Share Email Print

Proceedings Paper

Non-monotonic model-based system for scene interpretation
Author(s): Robert Abramczyk; Miao-Li M. Pai
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Model-based scene interpretation systems can use non-monotonic reasoning to resolve many of the inherent ambiguities and uncertainties present in real world image data. Model-based systems perform object recognition by efficiently matching features extracted from image data to corresponding features in known object models. This matching process is based on the accuracy of the extracted features. It is typically the case, however, that these features are themselves uncertain. This uncertainty is present because the image processing algorithms used for feature extraction do not consider global context, are noise sensitive, and use scene dependent parameters. Non-monotonic reasoning can resolve these uncertainties by identifying global inconsistencies and providing the means to recover from them. It does this by retracting invalid deductions based on the underlying causes of inconsistencies as they arise during the model matching process. A non-monotonic system can also predict the existence of additional features to complete a partial match.

Paper Details

Date Published: 1 January 1990
PDF: 8 pages
Proc. SPIE 1293, Applications of Artificial Intelligence VIII, (1 January 1990); doi: 10.1117/12.21049
Show Author Affiliations
Robert Abramczyk, Siemens Corporate Research, Inc. (United States)
Miao-Li M. Pai, Siemens Corporate Research, Inc. (United States)

Published in SPIE Proceedings Vol. 1293:
Applications of Artificial Intelligence VIII
Mohan M. Trivedi, Editor(s)

© SPIE. Terms of Use
Back to Top