Improved YOLOv5-based steel defect detection method

The invention discloses a steel defect detection method based on improved YOLOv5, and the method comprises the steps: obtaining a sample image of a steel defect, and carrying out the marking of different defect types of the sample image, thereby forming a steel defect data set; the YOLOv5 network model adopts a Focal EIoU Loss positioning loss function, a coordinate attention module is introduced in front of a prediction head of the YOLOv5 network model, then an improved YOLOv5 network model is constructed, and the steel defect data set is trained through the improved YOLOv5 network model to obtain a steel defect detection model; and inputting the obtained to-be-detected steel defect image into the steel defect detection model to obtain the defect type and defect position of the to-be-detected steel image. According to the invention, the detection cost and the misjudgment rate can be reduced, and the detection stability can be improved, so that the steel defect detection precision is improved. 本发明公开了一种基于改进的YO