High power LED lighting for CNN based image processing at frame rates of 10 kHz

Author

Blug, A. ; Jetter, V. ; Strohm, P. ; Carl, D. ; Hofler, H.

Author_Institution

IPM, Fraunhofer Inst. for Phys. Meas. Tech., Freiburg, Germany

fYear

2010

fDate

3-5 Feb. 2010

Firstpage

1

Lastpage

3

Abstract

CNN based cameras are able to process images in the kHz range in machine vision systems, as demonstrated for the closed loop control of laser welding processes. Other applications do not benefit from a comparable light source. This paper reports the current state of a LED based lighting for the inspection of cylindrical metallic surfaces on aluminum wires. Frame rates of 10 kHz and exposure times of 20 ??s have been achieved so far.

Keywords

cameras; cellular neural nets; closed loop systems; computer vision; inspection; laser beam welding; light emitting diodes; CNN based cameras; LED lighting; aluminum wires; cellular neural networks; closed loop control; cylindrical metallic surfaces; laser welding process; machine vision system; Cameras; Cellular neural networks; Control systems; Image processing; LED lamps; Light emitting diodes; Light sources; Machine vision; Optical control; Welding; Cellular neural networks; Image processing; Light-emitting diodes; Machine vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Nanoscale Networks and Their Applications (CNNA), 2010 12th International Workshop on

Conference_Location

Berkeley, CA

Print_ISBN

978-1-4244-6679-5

Type

conf

DOI

10.1109/CNNA.2010.5430333

Filename

5430333