| Summary: | 碩士 === 中華大學 === 機械與航太工程研究所 === 88 === As the electric circuit getting more compact and complicated, and the trace width getting finer and finer, the printed circuit board inspection processes become more difficult and time-consuming. As a result, traditional inspection method using bare eye with the aid of microscope or magnifier can no longer satisfy the need for high speed and high accuracy. To cope with this situation, an automated optical inspection system is developed in this research. By integrating image processing, stage and light source control techniques, the developed system can automatically inspect fiducial mark, trace, and pad with variety of shapes and sizes in an off-line fashion.
Generally speaking, the measuring of circle (fiducial mark, circular pad), rectangle (rectangular pad), and line width (trace) can be accomplished in three steps. Firstly, color segmentation techniques based on classification method are used to isolate the desired object from the selected area of color PCB image. In this research, four classifiers are investigated including minimal-distance classifier, Bayesian classifier, neural network, and fuzzy set theory. Secondly, edge detection technique is applied to collect all the edge points representing profile of the object. Finally, by adopting a suitable curve fitting technique, major dimensions of the pad can be obtained. As to the speed and accuracy, the experimental results show that the inspection method based on neural-network classifier possesses the highest measuring accuracy; however, the inspection method based on minimal-distance classifier can complete the measurement most quickly. It is worthwhile to notice that, no matter which segmentation method is used, the maximum error is less than 3% of the standard dimension for circular pad or 5% for rectangular pad. In addition to mentioned measurement function, the developed system can also be used to detect flaws, such as pinhole, protrusion, and spurious copper.
The developed automated optical inspection system is presented. Some important techniques established in this research, including color segmentation, curve fitting, and defect detection, are discussed in detailed in this thesis.
|
|---|
