The problem of automatically learning knowledge-directed control strategies is considered. In particular, the authors address the problem of learning object-specific recognition strategies from object descriptions and sets of interpreted training images. A separate recognition strategy is developed for every object in the domain. The goal of each recognition strategy is to identify any and all instances of the object in an image, and give the 3-D position (relative to the camera) of each instance. The goal of the learning process is to build a strategy that minimizes the expected cost of recognition, subject to accuracy constraints imposed by the user.<>
Learning 3D object recognition strategies
01.01.1990
459425 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Learning models for object recognition
IEEE | 2001
|Learning Models for Object Recognition
British Library Conference Proceedings | 2001
|CAD-Based Vision: Object Recognition in Cluttered Range Images Using Recognition Strategies
British Library Online Contents | 1993
|METHOD AND APPARATUS FOR PROVIDING OBJECT RECOGNITION LEARNING METHOD FOR OBJECT RECOGNITION
Europäisches Patentamt | 2025
|