Automated layer identification and segmentation of x-ray computer tomography imaged PCBs

The non-destructive inspection of Printed Circuit Boards (PCBs) through r-ray Computer Tomography (CT) is a recently developed method that offers several advantages over traditional inspection techniques. This method is non-invasive, quick, and offers high resolution, leading to significant improvements in inspection and repair efficiency. Post-image analysis is an important step in PCB inspection and has important practical significance for automatic positioning and determining the location of faults. Usually, the results of image segmentation are an important basis for PCB defect detection, and accurate segmentation results can effectively improve the efficiency and accuracy of PCB inspection and increase the level of automation. This paper discusses two innovative improvements for the automatic segmentation process: firstly determining which slices of an x-ray CT 3D PCB stack belong to which layer on a physical PCB in an automatic, generic and completely unsupervised way, which is verified on a 4-layer PCB; secondly proposing a level set-based image segmentation algorithm for the problem of gray scale inhomogeneity present in PCB CT. Experimental results on real PCB CT images with high aliasing and artifacts show that the proposed model can obtain better performance than the popular active contour models.