Translator Disclaimer
1 January 1990 Non-monotonic model-based system for scene interpretation
Author Affiliations +
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.
© (1990) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Robert Abramczyk and Miao-Li M. Pai "Non-monotonic model-based system for scene interpretation", Proc. SPIE 1293, Applications of Artificial Intelligence VIII, (1 January 1990);


Green space system design in Luoyang using Huff model
Proceedings of SPIE (November 04 2008)
Fundamental study on the error factor for sub 90nm OPC...
Proceedings of SPIE (November 15 2007)
Bayesian inference for model-based vision
Proceedings of SPIE (January 31 1992)
Model attraction in medical image object recognition
Proceedings of SPIE (April 16 1995)
Grouping-based recognition system
Proceedings of SPIE (January 31 1992)

Back to Top