图像处理在轴承荧光磁粉探伤中的应用研究  

Study on Application of Image Processing in Bearing Fluorescent Magnetic Detection

作　　者：张家栋[1] 张强[1] 霍凯[1] 

机构地区：[1]北京交通大学机械与电子控制学院,北京100044

出　　处：《计算机技术与发展》2009年第8期216-219,共4页Computer Technology and Development

基　　金：北京交通大学基金(KMJ06012532)

摘　　要：针对目前轴承荧光磁粉探伤人工观察方法存在的问题,介绍了一种轴承荧光磁粉探伤结果的自动识别方法。论述了裂纹图像识别处理方案的原理及流程,采用选定色彩范围的方法获取图像可疑成分,使用二值图像来表示图像的可疑成分与背景,主要应用数学形态学的方法对可疑图像进行处理,通过计算图像连通区域的大小和圆形度并与设定值比较来确认裂纹。算法在Matlab中进行测试,证实可有效识别出裂纹图像,说明自动轴承荧光磁粉探伤的可行性。Aim at the existing problems of the manual inspecting in bearing fluorescent magnetic detection, introduced an automatic identification method on the result of bearing fluorescent magnetic detection. Narrated in detail the principle and the flow of the crack pattern recognition processing plan, gain image suspicious ingredient by designates the color scope, used binary image to express the suspicious composition and background, mainly used mathematical morphology method to carry on the image processing, calculate the regional image＇s size and roundness then confirm the crack by compare them with the specified value. The algorithm is tested in Matlab, confirmed that may distinguish the crack image effectively, shows the feasibility of bearing automatic fluorescent magnetic particle detection.

关 键 词：荧光磁粉探伤 图像处理 数学形态学 自动识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TG115.28[自动化与计算机技术—计算机科学与技术]