Optimisation of automatic optical inspection on THT-PCB based on image segmentation and GLCM

ABSTRACT

Application Automatic Optical Inspection (AOI) is comprehensive in producing electronic circuits in the industry as an essential part of product assurance. Previous research created an AOI model for THT-PCB, which did not require complicated processing, and computers in vocational schools were able to process this model very well. However, this model cannot detect disturbed solder defects at solder joints. This study proposes optimising the AOI system to assist teachers in checking workpieces in soldering practicum, which significantly affects the industry’s need for students’ soldering skills. A Region of Interest (ROI) obtained by applying Image segmentation and log-polar transformation to the model. Then feature extraction had applied to the ROI using the Gray Level Cooccurrence Matrix (GLCM). The model verification shows an improved ability for disturbed soldering defects detection, which was not previously available on models. Accuracy and precision measurement for disturbed soldering defect detection by a correlation matrix gives a result of the accuracy of 91.75% and 90.20% precision. The fastest computation time measured on disturbed soldering defects detection is 800 milliseconds, while the total computing time is 2.8 seconds.

KEYWORDS:

• Automatic optical inspection
• local binary pattern
• SVM
• printed circuit board
• solder quality classification
• Through Hole Technology
• image segmentation

Disclosure statement

No potential conflict of interest was reported by the author(s).