Expert systems for image processing: knowledge-based composition of image analysis processes
Computer Vision, Graphics, and Image Processing
An Active Testing Model for Tracking Roads in Satellite Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning control strategies for object recognition
Symbolic visual learning
Object identification: a Bayesian analysis with application to traffic surveillance
Artificial Intelligence - Special issue: artificial intelligence 40 years later
Machine Learning
Model-Based Influence Diagrams for Machine Vision
UAI '89 Proceedings of the Fifth Annual Conference on Uncertainty in Artificial Intelligence
Journal of Cognitive Neuroscience
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Hi-index | 0.00 |
Many imaging systems seek a good interpretation of the scene presented - i.e., a plausible (perhaps optimal) mapping from aspects of the scene to real-world objects. This paper addresses the issue of finding such likely mappings efficiently. In general, an "(interpretation) policy" specifies when to apply which "imaging operators", which can range from low-level edge-detectors and region-growers through highlevel token-combination-rules and expectation-driven object-detectors. Given the costs of these operators and the distribution of possible images, we can determine both the expected cost and expected accuracy of any such policy. Our task is to find a maximally effective policy - typically one with sufficient accuracy, whose cost is minimal. We explore this framework in several contexts, including the eigenface approach to face recognition. Our results show, in particular, that policies which select the operators that maximize information gain per unit cost work more effectively than other policies, including ones that, at each stage, simply try to establish the putative most-likely interpretation.