基于阈值优化的带钢表面缺陷图像边缘检测研究  

Research on Edge Detection of Steel Plate Surface Defects Image Based on Threshold Optimizatio

作　　者：黎浩 汤勃[1] 孔建益[1] 王兴东[1] LI Hao;TANG Bo;KONG Jian-yi;WANG Xing-dong(School of Machinery and Automation Engineering,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学机械自动化学院,武汉430081

出　　处：《组合机床与自动化加工技术》2020年第8期122-125,共4页Modular Machine Tool & Automatic Manufacturing Technique

摘　　要：针对带钢表面缺陷图像光照不均而使得边缘检测困难的问题,分别使用顶帽变换和同态滤波对常规缺陷和低对比度缺陷进行去光照不均处理。接着,通过Otsu算法求出缺陷图像最佳阈值获取自适应的阈值改进边缘检测算法,即分别采用Sobel算法、Canny-Otsu算法进行常规缺陷和低对比度缺陷的图像分割。以带钢表面黑斑、划伤等典型缺陷为例进行了研究,结果表明算法取得了良好的效果。Aiming at the problem that edge detection is difficult due to uneven illumination of strip surface defect image,the conventional defect and low contrast defect are treated by top-hat transform and homomorphic filtering combined with wavelet algorithm respectively.The optimal threshold value of the defect image is obtained by the Otsu algorithm to improve edge detection algorithm.Sobel algorithm and Canny-Otsu algorithm are used for image segmentation of conventional defects and low contrast defects respectively.Taking the typical defects such as black spots and scratches on the surface of strip steel as an example,the results show that the algorithm has achieved good results.

关 键 词：顶帽变换 同态滤波 Otsu阈值分割 边缘检测 

分 类 号：TH16[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]