학술논문

Feature correlation for weld image-processing applications.
Document Type
Article
Source
International Journal of Production Research. 3/1/2004, Vol. 42 Issue 5, p975-995. 21p. 6 Black and White Photographs, 4 Diagrams, 2 Charts, 5 Graphs.
Subject
*Welding
*Process control systems
*Production control
*Manufacturing processes
*Computer integrated manufacturing systems
Image processing
Language
ISSN
0020-7543
Abstract
Template matching or correlation is an image-processing technique that searches for specific features or characteristics within an image. This paper describes the use of a configurable feature correlation method for the reliable processing of high quality digitized welding images in order to supply measurements for use with a closed loop control system. A generic approach has been adopted to produce a versatile and robust image-processing technique capable of analysing and providing measurements from images with different properties or characteristics. Low cost, commercially available image acquisition hardware was used, and the image-processing software development was undertaken using a commonly available PC-based visual programming environment. The general application of this work has been concerned with the demonstration of vision-based closed loop process control strategies for a series of different welding processes. Closing the process control loop in this manner is believed to represent a significant advancement of the vision-based remote viewing or 'monitoring' systems that are presently available. [ABSTRACT FROM AUTHOR]