TOFD 检测图像分割.pdf

机 械 工 程 学 报? CHINESE?JOURNAL?OF?MECHANICAL?ENGINEERING? 基于分水岭方法的超声?TOFD?检测图像分割?*? 盛朝阳 刚 铁 迟大钊? (哈尔滨工业大学 现代焊接生产技术国家重点实验室，哈尔滨? 150001)? 摘要：为了解决超声 TOFD 检测图像中缺陷识别的问题，分析了检测图像的特点，研究了图像自动分割的算法，其中包括图 像预处理及图像分割。首先提出了基于信号互相关算法的图像预处理方法，在此基础上，应用峰值搜索方法提取焊缝区域， 最后利用带控制标记符的分水岭变换对预处理的图像进行分割，从而识别出缺陷目标。利用提出的图像自动分割方法分割了 不同的超声 TOFD 检测图像。研究表明，基于信号互相关算法的图像校正方法在一定程度上可抑制检测图像的畸变，焊缝区 域图像的提取可减少图像分割过程的计算量，从局部极值的角度出发的带控制标记符的分水岭变换实现了缺陷目标的分割。 与基于阈值方法的图像分割结果相比，文中提出的图像自动分割算法较好地解决了近表面缺陷的识别问题，同时提出的方法 也可用于含多个缺陷的图像分割。 关键词：超声 TOFD? 缺陷识别 图像分割 分水岭 中图分类号：TG115.28? Segmentation?of?Ultrasonic?TOFD?Testing?Image Based?on?Watershed? Method? SHENG?Zhaoyang? GANG?Tie? (State?Key?Lab?of?Advanced?Welding?Production?Technology,?Harbin?Institute?of?Technology,?No.92,?Dazhi?Street,? Harbin,?150001,?China)? Abstract：In?order?to?identify the?defect?in?the?testing?image?obtained?by?the?Ultrasonic?TOFD?method,?by?analyzing?the?feature?of? the? testing? image,? the? automatic? algorithm? for? image? segmentation? was? studied,? including? the? image? preprocessing? and? the? segmentation.?First,?the image?preprocessing?method?was?presented,?which?was?based?on?the?signal?cross-correlation?algorithm.?Then? the?extraction?of?weld?region?based?on?the searching?extreme?points?of?signals?was expressed.?After?that the?watershed transform with? the?control? marker?was? applied?to? segment? the?preprocessed?image,? thereby? the? defect? was?extracted.? Different? Ultrasonic? TOFD? testing? images? were? segmented? by? the? presented? automatic? image? segmentation? method.? The? results? show? that? the? signal? cross-correlation?algorithm basically suppresses?t