QUARTERLY JOURNAL OF THE JAPAN WELDING SOCIETY
Online ISSN : 2434-8252
Print ISSN : 0288-4771
Application of Image Noise Elimination by Neural Network
signal Processing for Image of Weld Joint Configuration
Katsunori InoueShigetaka KannanBunkei Kyou
Author information
JOURNAL FREE ACCESS

1995 Volume 13 Issue 4 Pages 567-572

Details
Abstract

On using the signal processing ability of Backpropagation Model of Neural Network, the noise elimination is performed on the image of a joint part of arc welding. The object image, which is obtained by the slit light slice method, is often used for the detection of joint configurationis on the purpose of welding automation. The noise caused by the welding arc is superimposed on the image and disturbs the detection. Such noise is eliminated through the learning process of Neural Network which is carried out for the noise imposed input images and the noiseless teacher images. The structure of the network, the image input method, the selection of the teacher image and the method to recover the resolution of the processed result are investigated experimentally. It is shown that the noise elimination is successfully done as the result.

Content from these authors
© by JAPAN WELDING SOCIETY
Previous article Next article
feedback
Top