ISSN:
1432-1769
Schlagwort(e):
industrial vision
;
knowledge-based system
;
image processing
;
knowledge acquisition
;
object recognition
Quelle:
Springer Online Journal Archives 1860-2000
Thema:
Informatik
Notizen:
Abstract This paper introduces a knowledge-based vision system for industrial environments. It is designed to control a cell in an assembly system. The images from the environment are taken as gray scale images. Based on a single image, the system has to recognize type and position of the recorded parts and to control their placement in the environment for further manipulation. This requires the explicit representation of rich task-specific knowledge. The effort to adapt our system to new tasks is very small. Thus, it is very important that the system is able to support major parts of the activities that are necessary for the acquisition of new knowledge. The system consists of three components-image segmentation, knowledge acquisition, and matching-which are described in detail. All the methods presented were tested using different parts of an electric motor as an example.
Materialart:
Digitale Medien
URL:
http://dx.doi.org/10.1007/BF01211848
Permalink
