On the optimal detection of curves in noisy pictures
Communications of the ACM
An intelligent robot with cognition and decision-making ability
IJCAI'71 Proceedings of the 2nd international joint conference on Artificial intelligence
A versatile computer-controlled assembly system
IJCAI'73 Proceedings of the 3rd international joint conference on Artificial intelligence
A Model-Based Vision System for Industrial Parts
IEEE Transactions on Computers
Hi-index | 0.00 |
This paper describes a versatile machine vision system that can recognize a variety of complex industrial parts based on the previously learned models of them. It proposes a model guided approach for recognition in which models of objects direct recognition process by suggesting the features to be examined next and their predicted locations. For the system to be readily applied to new tasks, it can automatically generate the models of objects while a human operator showing example parts and teaching important features of them interactively on displays. The system has been applied to various sets of parts of small industrial gasoline engines and the result was satisfactory.