Steel surface defect detection based on improved YOLOv8

Abstract Addressing the issue of imbalance between detection accuracy and speed in current steel surface defect detection methods, we propose an improved YOLOv8-based algorithm, named YOLO-SSD, for steel surface defect detection. This algorithm replaces the downsampling module with a SPD-Conv module in the backbone network and introduces the CBAM attention module to enhance feature extraction capability and small object detection ability. Additionally, in the neck network, the C2f module is replaced with a C2f-Ghost module, which not only lightweightens the neck module but also improves the utilization of computational resources. Experimental results on the NEU-DET dataset demonstrate that compared to the original YOLOv8 algorithm, the average detection accuracy of the YOLO-SSD algorithm for steel surface defect detection has been improved by 2.8%, with a frame per second (FPS) reaching 96. Compared to current mainstream steel surface defect detection algorithms, the improved detection algorithm can enhance the detection accuracy of the defect detection model without compromising detection speed.