基于Canny算法的列车轴承内圈外表面缺陷检测  

Defect Detection of Outer Surface of Rrain Bearing Inner Ring Based on Canny Algorithm

作　　者：石炜[1] 王涛[1] SHI Wei;WANG Tao(School of Mechanical Engineering Inner Mongolia University of Science and Technology Inner,Baotou Mongolia 014010)

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：《数字技术与应用》2018年第5期134-136,共3页Digital Technology & Application

基　　金：内蒙古科技厅应用与研究开发计划项目一高新技术领域科技计划重大项目(20130302)

摘　　要：目前轴承表面缺陷检测操作的不足之处是速度慢、精确度低、人工成本高,本文提出一种基于机器视觉轴承内圈外表面缺陷识别方法。首先获取高质量的彩色图像并将其转换为灰度图,然后对输入图像进行预处理,采用直方图分割法求出最佳阈值对图像进行二值化处理,最后利用目标标记与边缘检测算法对图像信号进行缺陷识别与分析。实验结果表明,该方法实现计算机对缺陷图像的理解和自动识别,能够正确检测表面缺陷几何特征,并具有一定的适用性。此方法可以克服人工检测方法的许多不足,提高检测精度和速度,为后期的缺陷识别提供了技术支持。At present, the defects of the bearing surface defect detection operation are slow speed, low accuracy and high artificial cost. This paper presents a method of identifying the outer surface defects of the inner ring of the machine vision bearing. First of all, the high quality color image is obtained and converted into gray scale, then the input image is preprocessed. The image is processed two values by the histogram segmentation method.Finally, the image signal is identified and analyzed by target marker and edge detection algorithm. The experimental results show that this method can realize the understanding and automatic recognition of the defective images, and can correctly detect the geometric features of the surface defects, and has certain applicability. This method can overcome many shortcomings of manual detection methods, improve detection accuracy and speed, and provide technical support for later defect recognition.

关 键 词：机器视觉 目标标记 边缘检测 表面缺陷 

分 类 号：TH16[机械工程—机械制造及自动化] TH133.33