YOLOv8-TDD: An Optimized YOLOv8 Algorithm for Targeted Defect Detection in Printed Circuit Boards

An enhanced approach for detecting defects in Printed Circuit Boards (PCBs) using a significantly improved version of the YOLOv8 algorithm is proposed in this research, the proposed method is referred to as YOLOv8-TDD (You Only Look Once Version8-Targeted Defect Detection). This novel approach integrates cutting-edge components such as Swin Transformers, Dynamic Snake Convolution (DySnakeConv), and Biformer within the YOLOv8 architecture, aiming to address and overcome the limitations associated with traditional PCB inspection methods. The YOLOv8-TDD adaptation incorporates Swin Transformers to leverage hierarchical feature processing with shifted windows, enhancing the model's efficiency and capability in capturing complex image details. Dynamic Snake Convolution is implemented to dynamically adapt filter responses based on the input feature maps, offering tailored feature extraction that is highly responsive to the varied textures and defects in PCBs. The Biformer, with bidirectional processing capability, enriches the model's contextual understanding, providing a comprehensive analysis of the PCB images to pinpoint defects more accurately. Experimental results demonstrate that YOLOv8-TDD model, achieves a precision of 97.9%, a mean Average Precision (mAP0.5) of 95.71%. This enhanced model offers significant potential for practical applications in PCB manufacturing, promising to elevate quality control standards through more reliable defect detection.