This study was conducted to verify the hypothesis of the possibility to design an Automated Defect Detection system at a budget using image processing software. Focusing mainly on simplicity of integration with the capability to inspect a high variation of PCB with less user input. Reference comparison method was utilized to construct the defect detection algorithm where a defect free reference PCB gets compared with an inspection image to identify defects and anomalies. The paper discusses the range of possible defects for inspection on non-assembled PCBs, suggests methods for image processing and presents a final inspection algorithm, including their testing. The defect detections system showed high accuracy in detecting defects under ideal testing conditions and was unreliable in detecting defects in real-life testing conditions. Even though the current system may be sufficient for an experimental prototype system more improvements need to be done to be used in the industry.
Date of Degree
Master of Science (MS)
Manufacturing Engineering Technology
Automotive and Manufacturing Engineering Technology
Science, Engineering and Technology
Munaweera Tanthirige, N. K. D. S. (2022). Printed circuit board defect detection using image processing [Master’s thesis, Minnesota State University, Mankato]. Cornerstone: A Collection of Scholarly and Creative Works for Minnesota State University, Mankato. https://cornerstone.lib.mnsu.edu/etds/1242/
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.