Automatic rule generation for high-level vision
Frank Chung-Hoon Rhee, Raghu J. Krishnapuram · NASA STI Repository (National Aeronautics and Space Administration) · 1992
Many high-level vision systems use rule-based approaches to solving problems such as autonomous navigation and image understanding. The rules are usually elaborated by experts. However, this procedure may be rather tedious. In this paper, we propose a method to generate such rules automatically from training data. The proposed method is also capable of filtering out irrelevant features and criteria from the rules.