摘要
由于焊缝缺陷图像存在噪声多、对比度不高、图像边缘模糊等缺点,从而影响到焊缝缺陷区域特征的提取,不利于焊缝缺陷的分类和识别。文中针对焊缝缺陷图像的复杂性,提出了一种有效提取焊缝缺陷区域特征的方法。首先对焊缝图像进行图像预处理、图像分割、缺陷图像背景去除,提取到焊缝缺陷区域;然后采用8连通区域标记的方法对处理之后的二值化缺陷图像进行标记;最后对每一个标记后的缺陷区域的周长、面积、圆形度等几何参数进行提取。试验结果表明,这种图像处理的方法能较准确地提取出焊缝缺陷图像的特征,具有良好的适应性与实用性。
There are many defects in welding images such as noise,low contrast,blurred edges,which affect feature extraction of weld defect regions and go against classification and recognition of weld defect.To deal with the complexity of weld defect images,an effective method for extracting the characteristic of welding defect regions was proposed in the paper.Firstly,image preprocessing,image segmentation,image background removal were carried on to extract weld defect area.And then 8 connected component labeling method was used to mark processed binary images.Lastly,parameter characteristics including perimeter,area,circular degree and others were extracted.The experimental results showed that the image processing method could accurately extract the characteristics of weld defect images.It held good adaptability and practicability.
作者
李金燕
李春祥
王锡岭
LI Jin-yan;LI Chun-xian;Wang Xi-ling(Jiangsu Jiaotong College,Zhenjiang 212018,Jiangsu pro.,China;Suzhou Institute of Technology,Jiangsu University Science and Technology,Zhangjiagang 215600,Jiangsu pro.,China)
出处
《焊接技术》
2018年第11期78-82,I0002,共6页
Welding Technology
关键词
焊缝缺陷
特征提取
图像处理
缺陷标记
weld defect
feature extraction
image processing
defect marking
