列车轴承表面缺陷图像的边缘检测研究  

Research on Edge Detection of Train Bearing Surface Defect Image

作　　者：石炜[1] 杨晶安 张显宇 赵岩 SHI Wei;YANG Jing'an;ZHANG Xianyu;ZHAO Yan(School of Mechanical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China)

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010

出　　处：《机械工程师》2024年第8期8-12,共5页Mechanical Engineer

基　　金：2018年内蒙古自治区自然科学基金“基于机器视觉的机械零部件曲面图像检测关键技术研究”(2018LH05024)。

摘　　要：为了实现含有噪声的列车滚子轴承内圈外表面缺陷图像边缘信息的机器视觉检测,提出一种改进Canny算子与改进的新型形态学算法融合的边缘检测算法,采用一种新的自适应中值滤波器替换高斯滤波器进行图像降噪,并拓展多方向梯度模板计算图像的幅值。使用最大类间方差法自适应获得最佳阈值,减少伪边缘的出现,进一步提高算法的适应性。对两种方法检测到的子图像信息熵进行图像融合,获得最终的边缘检测图像。试验结果表明,对比单一地使用Canny算子和数学形态法,文中采用的融合算法具有更好的自适应性和检测性能。To realize the machine vision detection of the edge information of the outer surface defect image of the train roller bearing inner race containing noise,this paper proposes an edge detection algorithm based on the fusion of the improved Canny operator and the improved new morphological algorithm.A new adaptive median filter is used to replace the Gaussian filter for image noise reduction.The multi-directional gradient template is extended to calculate the image amplitude.The maximum between-class variance method is used to adaptively obtain the best threshold,and reduce the appearance of false edges,and further improve the adaptability of the algorithm.The final edge detection image is obtained by image fusion according to the sub-image information entropy detected by the two methods.The experimental results show that the fusion algorithm in this paper has better adaptability and detection performance than the single use of Canny operator and mathematical morphology.

关 键 词：CANNY 自适应中值滤波 最大类间方差 数学形态学 边缘检测 

分 类 号：TH133.33[机械工程—机械制造及自动化] TP277[自动化与计算机技术—检测技术与自动化装置]