Abstract
A simple method is proposed for comparing the relative performance of machine vision systems designed for programmable automation. Some major performance criteria are the degree of discrimination between patterns and the execution time required to determine the identity, the state, and the position of workpieces.
The method is based on the use of a small set of two-dimensional test figures with readily-reproducible silhouettes. Workpieces with multiple internal regions of interest are simulated by a circular disc with multiple holes, increasing complexity represented by an increase in the number of holes, with a consequent increase in the required processing time for analysis.
The method of measurement is described, the geometric test shapes are illustrated, and typical performance measurements are reported for a commercial machine vision system.
Reprinted by courtesy of the Society of Manufacturing Engineers, Dearborn, Michigan, USA from SME Technical Paper MS 80–700.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. G. Dodd and L. Rossol, ‘Computer Vision and Sensor-Based Robots’, Plenum Press, New York (1979).
C. A. Rosen and D. Nitzan. ‘Use of Sensors in Programmable Automation’, Computer, Vol. 10, No. 12 (1977).
G. Gleason and G. J. Agin, ‘A Modular Vision System for Sensor-Controlled Manipulation and Inspection’, Proc. 9th Int. Symp. on Industrial Robots, Washington, DC, (March 1979).
M. R. Ward, L. Rossol, S. W. Holland and R. Dewar, ‘Consight — A Practical Vision-Based Robot Guidance System’, Proc. 9th Int. Symp. on Industrial Robots, Washington, DC (March 1979).
J. P. Foith, H. Geisselmann, U. Lubbert and H. Ringshauser, ‘A Modular System for Digital Imaging Sensors for Industrial Vision: Proc. 3rd CISM IFToMM. Symp. on Theory and Practice of Robots and Manipulators’,Udine, Italy (September 1978).
J. P. Foith, ‘A TV-Sensor for Top-Lighting and Multiple Part Analysis, 2nd/FAC/IFIP Symp. on Information Control Problems in Manufacturing Technology, Stuttgart, Germany (October 1979).
G. J. Agin, ‘Computer Vision Systems for Industrial Inspection and Assembly’, Computer, Vol. 13, No. 5 (May 1980).
Model VS-100 Machine Vision System, Machine Intelligence Corporation, Palo Alto, California.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1983 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Rosen, C.A., Gleason, G.J. (1983). Evaluating Vision System Performance. In: Pugh, A. (eds) Robot Vision. International Trends in Manufacturing Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-09771-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-662-09771-7_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-09773-1
Online ISBN: 978-3-662-09771-7
eBook Packages: Springer Book Archive