Research and Application of Machine Vision Technology in Workpiece Detection and Recognition

DOI

10.2991/acsr.k.191223.036How to use a DOI?

Keywords

defect defecting, cluster mode, image identification

Abstract

This paper adopt image recognition to realize the defect detection of small probability defect parts in cluster mode. In this mode, parts with small probability of defects were identified one by one to be recognized. Different lighting conditions were tried to determine what kind of lighting should be used for auxiliary lighting. By means of steps such as gray scale stretching and threshold segmentation, the collected image could be used as binary graph suitable for defect detection after preprocessing. The characteristics of the bolt itself were used as the identification condition to match the measured item with the template. Then the difference information between the matching result and the template was calculated by difference shadow method. And according to this information, whether the product to be tested is qualified is determined.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiangwei Chen
AU  - Tiantian Zhang
PY  - 2019
DA  - 2019/12/24
TI  - Research and Application of Machine Vision Technology in Workpiece Detection and Recognition
BT  - Proceedings of the 2019 International Conference on Big Data, Electronics and Communication Engineering (BDECE 2019)
PB  - Atlantis Press
SP  - 153
EP  - 159
SN  - 2352-538X
UR  - https://doi.org/10.2991/acsr.k.191223.036
DO  - 10.2991/acsr.k.191223.036
ID  - Chen2019
ER  -