3DPO: A three-dimensional part orientation system
International Journal of Robotics Research
The representation, recognition, and locating of 3-d objects
International Journal of Robotics Research
A Method for Attribute Selection in Inductive Learning Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
3-D Object Recognition Using Bipartite Matching Embedded in Discrete Relaxation
IEEE Transactions on Pattern Analysis and Machine Intelligence
An interference matching technique for inducing abstractions
Communications of the ACM
Induction of relational productions in the presence of background information
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
Knowledge acquisition from structural descriptions
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
Induction of concepts in the predicate calculus
IJCAI'75 Proceedings of the 4th international joint conference on Artificial intelligence - Volume 1
IJCAI'79 Proceedings of the 6th international joint conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
Object recognition requires complicated domain-specific rules. For many problem domains. it is impractical for a programmer to generate these rules. A method for automatically generating the required object class descriptions is needed - this paper presents a method to accomplish this goal. In our approach. the supervisor provides a series of example scene descriptions to the system. with accompanying object class assignments. Generalization rules then produce object class descriptions. These rules manipulate non-symbolic descriptors in a symbolic framework; the resulting class descriptions are useful both for object recognition and for providing clear explanations of the decision process. We present a simple method for maintaining an optimal description set as new examples (possibly of previously unseen classes) become available. providing needed updates to the description set. Finally. the system's performance is shown as it learns object class descriptions from realistic scenes - video images of electronic components.