Learning 3D object recognition strategies
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 320-324
- https://doi.org/10.1109/iccv.1990.139541
Abstract
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.Keywords
This publication has 1 reference indexed in Scilit:
- Induction of decision treesMachine Learning, 1986