A novel PCB surface defect detection method based on separated global context attention to guide residual context aggregation.

In the production and manufacturing of Printed Circuit Boards (PCBs), defects can arise negatively impact to both product performance and usability. To tackle the issue of false detections stemming from a high volume of small defects and complex backgrounds in PCBs, we propose SRN_Net, an innovative small object detection framework specifically designed for PCB defect identification scenarios. Firstly, an advanced Separated Global Context Attention (SGC) mechanism is introduced to enhance the model's attention to small targets and improve the detection accuracy of the model for small targets. Furthermore, a Residual Context Aggregation (RCA) module is seamlessly integrated into the network's neck, effectively attenuating the disruptive influence of irrelevant background noise during the fusion of small target features. Lastly, a No Stride Convolution (NSC) technique is deployed in both the trunk and neck of the network and meticulously designed to enhance small target detection accuracy by minimizing feature loss during the convolution process. Extensive experiments on the PCB dataset demonstrate that, compared to state-of-the-art algorithms, SRN_Net achieves increases of 1.1% in Precision, 1.3% in Recall, 0.6% in mAP@0.5, and 4.6% in mAP@0.5:0.95, highlighting its superior performance in defect detection. To demonstrate the efficacy of SRN_Net across other industrial datasets, we conducted an additional evaluation on the NEU surface defect dataset, achieving an mAP of 75.8%. This work contributes to advancing small object detection accuracy and robustness in practical applications. The code will be available at https://github.com/Zhaohuohuo666/SRN .