Using object descriptions in a schema network for machine vision
Using object descriptions in a schema network for machine vision
The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty
ACM Computing Surveys (CSUR)
Computational Approaches to Image Understanding
ACM Computing Surveys (CSUR)
Integrating non-semantic knowledge into image segmentation processes
Integrating non-semantic knowledge into image segmentation processes
Processing dynamic image sequences from a moving sensor (artificial intelligence, motion)
Processing dynamic image sequences from a moving sensor (artificial intelligence, motion)
A retrospective view of the Hearsay-II architecture
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2
Model representations and control structures in image understanding
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2
A semantics-based decision theory region analyzer
IJCAI'73 Proceedings of the 3rd international joint conference on Artificial intelligence
| Hi-index | 0.00 |
Expert system technology has been successfully applied to many practical problems, but. there has been little evidence of transfer to computer vision. In this paper we discuss some of the problems confronting computer vision and present an approach to the development of general knoledge-based vision systems. The primary mechanism is a rule-based approach for the generation of initial object hypotheses, which allow focus of attention strategies. The rule set, applied to the attributes of the lines, regions, and surfaces in an intermediate symbolic representation, is constructed interactively with visual feedback to the user. Simples rules are defined as ranges over a feature value which are converted to a vote for an object label; complex rules are constructed via a functional combination of the output from the simple rules. The rule-based object hypotheses are used to invoke more complex knowledge-based strategies for verifying and extending the partial interpretation. We conclude with some principles which could be used to guide knowledge-based vision research.