Watershed Algorithm for PCB Automatic Optical Inspection Systems

DOI

10.2991/icmii-15.2015.56How to use a DOI?

Keywords

Machine Vision; Watershed Algorithm; Region Segmentation; Local Extreme; Defect Recognition

Abstract

The production of the PCB board is related to the development of the electronics industry. In order to improve the quality of the circuit board, Startingfrom the detection of single PCB board and replacing the traditional manual inspection mode through using the methods of machine vision is to improve the efficiency. For “the outer layer inspection” link of the PCB substrate in the generalized processing,the use of machine vision detection algorithm based on watershed algorithm and the integration of organic into existing automated optical inspection equipment not only ensureshigh efficiency but also reduces the artificial false detection rate through replacing the human eye with the use of the machine vision. Different from traditional detection algorithm, the advantages of watershed algorithm are mainly reflected in the extractingsegmentation target area pixel value and regions by calculation and comparison of local extreme position to identify deficiencies and give the type of defect identification purposes. Experimental results show that the use of this method is effective to improve the efficiency and accuracy of defect recognition.

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  - Ping Feng
AU  - Qiyuan Gong
AU  - Tao Cheng
PY  - 2015/10
DA  - 2015/10
TI  - Watershed Algorithm for PCB Automatic Optical Inspection Systems
BT  - Proceedings of the 3rd International Conference on Mechatronics and Industrial Informatics
PB  - Atlantis Press
SP  - 310
EP  - 318
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmii-15.2015.56
DO  - 10.2991/icmii-15.2015.56
ID  - Feng2015/10
ER  -