Quality Evaluation and Automatic Classification in Resistance Spot Welding by Analyzing the Weld Image on Metal Bands by Computer Vision
- Resource Type
- Article
Text
- Authors
- Yang ou; Li yueping
- Source
- International Journal of Signal Processing, Image Processing and Pattern Recognition, 05/30/2015, Vol. 8, Issue 5, p. 301-314
- Subject
- Artificial Neural Network
spot weld
computer vision
Image features extraction
image Segmentation.
- Language
- 영어(ENG)
- ISSN
- 2005-4254
This paper introduces a novel method for the quality evaluation of resistance spot welds. The evaluation is based on computer vision methods, which allow nondestructive on-line real-time processing. The input of the system is the image of a weld imprint on a metal band which covers the electrodes against wear and soiling. In order to find the position of the resistance spot welds, we describe an image registration method based on geometric pattern matching for alignment system in metal parts. Further we extract features describing the shape of localized objects in segmented images .Using these shape descriptors (geometric feature) we classify the defects by Artificial Neural Network.