Steel surface defect detection based on lightweight YOLOv7

作     者：Shi Tao Wu Rongxin Zhu Wenxu Ma Qingliang 

作者机构：School of Electrical Engineering and Automation， Tianjin University of Technology North China University of Science and Technology， College of Electrical Engineering Guangzhou Institute of Measurement and Testing Technology 

出 版 物：《Optoelectronics Letters》 (光电子快报(英文))

年 卷 期：2025年

学科分类：08[工学] 080203[工学-机械设计及理论] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 

基　　金：supported by the National Natural Science Foundation of China (No. 62103298) the Natural Science Foundation of Hebei Province (No. F2018209289) 

摘      要：Aiming at the problems of low detection efficiency and difficult positioning of traditional steel surface defect detection methods， a lightweight steel surface defect detection model based on YOLOv7 is proposed. First， a CSS Block module is proposed， which uses more lightweight operations to obtain redundant information in the feature map， reduces the amount of computation， and effectively improves the detection speed. Secondly， the improved SPPCSPC structure is adopted to ensure that the model can also pay attention to the defect location information while predicting the defect category information， obtain richer defect features. In addition， the convolution operation in the original model is simplified， which significantly reduces the size of the model and helps to improve the detection speed. Finally， using EIOU Loss to focus on high-quality Anchors， speed up convergence and improve positioning accuracy. Experiments were carried out on the NEU-DET steel surface defect dataset. Compared with the original YOLOv7 model， the number of parameters of this model was reduced by 40%， the FPS reached 112， and the average accuracy reached 79.1%.， the detection accuracy and speed have been improved， which can meet the needs of steel surface defect detection.