The side threaded surface of metal threaded kits is easily damaged by collision during handling, or by the tool marks of the cutting tool during processing. Due to the fact that cylindrical kits are easy to roll and are small and difficult to hold, even with strong light and microscope equipment, it is still difficult to detect with the naked eye, and it is easy to miss and miss detection.Using Solomon SolVision, AI models are trained with images of metal kit defects, and Segmentation technology is used to learn the characteristics of tool marks and collision defects. After the AI model is trained, it can easily detect small metal defects that are difficult to identify with the naked eye. The kits are picked out to improve the overall quality of the shipped metal kits.