Research on Surface Defect Detection Through Yolov8

This study utilizes the YOLOv8 framework, which focuses on identifying six types of common defects on the surface of hot-rolled strip: cracks (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{C r}$</tex>), inclusions (In), spots (Pa), pitted surfaces (PS), oxidized layers (RS), and scratches <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\text{Sc})$</tex>. The experimental results show that this system is not only faster but also more accurate in recognizing various surface defects compared to conventional techniques. The YOLOv8 model achieves high mAP values on both the training and test sets, proving its effectiveness in defect detection tasks. This study not only verifies the potential of the YOLOv8 algorithm in industrial applications, but also provides a new direction for future research in computer vision and machine learning.