Quantitative Detection of Micro Hole Wall Roughness in PCBs Based on Improved U-Net Model

Abstract The current method for inspecting microholes in printed circuit boards (PCBs) involves preparing slices followed by optical microscope measurements. However, this approach suffers from low detection efficiency, poor reliability, and insufficient measurement stability. Micro-CT enables the observation of the internal structures of the sample without the need for slicing, thereby presenting a promising new method for assessing the quality of microholes in PCBs. This study integrates computer vision technology with computed tomography (CT) to propose a method for detecting microhole wall roughness using a U-Net model and image processing algorithms. This study established an unplated copper PCB CT image dataset and trained an improved U-Net model. Validation of the test set demonstrated that the improved model effectively segmented microholes in the PCB CT images. Subsequently, the roughness of the holes’ walls was assessed using a customized image-processing algorithm. Comparative analysis between CT detection based on various edge detection algorithms and slice detection revealed that CT detection employing the Canny algorithm closely approximates slice detection, yielding range and average errors of 2.92 and 1.64 μm, respectively. Hence, the detection method proposed in this paper offers a novel approach for non-destructive testing of hole wall roughness in the PCB industry.