PCB Defect Detection Model Based on Intrinsic Feature Decomposition and Multilevel Fusion Against Image Uncertainty

The production quality of printed circuit boards (PCBs) is critical to ensure that electronic products work properly. Images acquired in complex environments with image uncertainties such as low contrast and multiple noises affect the performance of computer vision-based surface defect detection of PCBs. For datasets with image uncertainty, this paper proposes a classification model based on intrinsic feature decomposition and multi-level fusion for PCBs defect detection. Firstly, the modified Retinex decomposition is used to generate multi-layer reflection and shading maps that are more appropriate to the classification task. A grading sparse encoder is designed for the reflection map to characterize the image features. Next, a bilateral convolutional filter with multi-dimension transformer is used to remove the noise information present in the shading map. Finally, feature fusion is performed by a multi-layer attention module of channel attention and pixel attention for classification to improve the utilization of defective feature information. By comparing the proposed algorithm with other advanced algorithms in a dataset set with different luminance ratios, it is demonstrated that the proposed algorithm can effectively improve the accuracy of PCBs defect detection.