Research on the Detection Algorithm of Workpiece Surface Defects Based on Machine Vision

DOI

10.2991/tmcm-15.2015.11How to use a DOI?

Keywords

region growing; remove the shadow; defect detection; threshold segmentation

Abstract

It is important to evaluate the workpiece whether the surface is defective or not. Because of the shadow area due to light angle by taking pictures, false edges are obtained. It will lead to that the real edge will be mistaken for surface scratches. Based on region growing, this paper introduces a new algorithm which is proposed to remove the shadow region, After the Gauss filter, the real defect of the component surface is obtained by the threshold segmentation. The experiments show that this method is suitable for a variety of scenarios of component surface defect detection. And it has the characteristics of high efficiency, stability and high precision.

Copyright

© 2015, 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  - Yuntao Zhang
AU  - Xiaorong Chen
AU  - Yin Yi
PY  - 2015/11
DA  - 2015/11
TI  - Research on the Detection Algorithm of Workpiece Surface Defects Based on Machine Vision
BT  - Proceedings of the 2015 International Conference on Test, Measurement and Computational Methods
PB  - Atlantis Press
SP  - 40
EP  - 43
SN  - 2352-538X
UR  - https://doi.org/10.2991/tmcm-15.2015.11
DO  - 10.2991/tmcm-15.2015.11
ID  - Zhang2015/11
ER  -