A Novel Algorithm for Detecting Air Holes in Steel Pipe Welding Based on Hopfield Neural Network

Author

Weixin, Gao ; Nan, Tang ; Xiangyang, Mu

Author_Institution

Xian Shiyou Univ., Xian

Volume

1

fYear

2007

fDate

July 30 2007-Aug. 1 2007

Firstpage

79

Lastpage

83

Abstract

The paper segment x-ray images of steel pipe welding to assess the quality of welding. Image segmentation is posed as an optimization problem, and is correlated with the energy function of the multistage Hopfield neural network. The algorithm for optimization and the principle of selecting coefficient are also given. The algorithm is easy to be programmed. As an application, we successfully segment some real industrial welding x-ray images.

Keywords

Hopfield neural nets; X-ray imaging; image segmentation; object detection; optimisation; pipes; steel industry; welding; multistage Hopfield neural network; optimization problem; steel pipe welding air hole detection algorithm; x-ray image segmentation; Clustering algorithms; Gray-scale; Hopfield neural networks; Image segmentation; Neural networks; Steel; Welding; X-ray detection; X-ray detectors; X-ray imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, 2007. SNPD 2007. Eighth ACIS International Conference on

Conference_Location

Qingdao

Print_ISBN

978-0-7695-2909-7

Type

conf

DOI

10.1109/SNPD.2007.425

Filename

4287478