传感技术学报2025，Vol.38Issue(4)：651-657,7.DOI:10.3969/j.issn.1004-1699.2025.04.011
基于图像处理的轴承套圈黑块缺陷检测
Detection of Black Block Defect of Bearing Ring Based on Image Processing
摘要
Abstract
In order to solve the problem of low detection accuracy caused by the difficulty in contour extraction and excessive surface-inde-pendent features,a comprehensive method based on image processing is proposed.Firstly,the preprocessed image is enhanced by the im-proved Gaussian filter so as to improve the contrast between the bearing ring and background.The contour tracking and least square fitting are used to determine the ROI position information of the ring,and the polar coordinate transformation is used to obtain the rectangular im-age of the end face.Irrelevant features on the rectangular image are eliminated according to the imaging characteristics of the ring,and double thresholds are used to determine whether there are defects.The experimental results show that the detection accuracy of defective bearing ring is up to 100.00％,the comprehensive detection accuracy is up to 98.47％,and the method has good real-time performance.关键词
图像增强/高斯滤波/缺陷检测/轴承套圈Key words
image enhancement/Gaussian filter/defect detection/bearing ring分类
信息技术与安全科学引用本文复制引用
张建新,黄伟嘉,钱淼..基于图像处理的轴承套圈黑块缺陷检测[J].传感技术学报,2025,38(4):651-657,7.基金项目
浙江省科技厅重点研发项目(2022C01188,2023C01158) （2022C01188,2023C01158）
