焊缝缺陷图像特征提取的研究
|
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.
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.
引文
[1]罗爱民,沈才洪,易彬.基于改进二叉树多类SVM的焊缝缺陷分类方法[J].焊接学报,2010,31(7):51-54.
[2]吴一全,叶志龙.基于Contourlet和KPCA的焊接缺陷图像特征提取[J].焊接学报,2014,35(7):18-21.
[3]叶志龙.基于图像处理的焊接缺陷自动检测方法研究[D].江苏南京:南京航空航天大学,2013.
[4]梁鹏.X射线焊缝图像缺陷自动提取与识别技术研究[D].江苏南京:南京航空航天大学,2012.
[5]Shao J X,Du D,Shi H,et al.A fast and adaptive method for automatic defect detection in various real-time X-ray imaging systems[J].China Welding(English Edition),2012,21(1):8-12.
[6]云海姣,吴志勇.结合直方图均衡和模糊集理论的红外图像增强[J].计算机辅助设计与图形学学报,2015,27(8):1 499-1 505.
[7]陈莹,朱明.多子直方图均衡微光图像增强及FPGA实现[J].中国光学,2014,7(2):225-233.
[8]杨勇,黄淑英.一种改进的Pal和King模糊边缘检测算法[J].仪器仪表学报,2008,29(9):1 919-1 922.
[9]Theoharatos Ch,Economou G.Color edge detection using the minimal spanning tree[J].Pattern Recognition,2005,38(4):603-606.
[10]Otsu N.The shold selection method from gray-level histogram[J].IEEE Transactions on Systems,Man and Cybernetics,1979,9(1):62-66.
[11]Mehnert A,Jackway P.An improved seeded region growing algorithm[J].Pattern Recognition Letters,1997,18(10):1 065-1 071.
[12]刘奇琦,龚晓峰.一种二值图像连通区域标记的新方法[J].计算机工程与应用,2012,48(11):178-180.
[2]吴一全,叶志龙.基于Contourlet和KPCA的焊接缺陷图像特征提取[J].焊接学报,2014,35(7):18-21.
[3]叶志龙.基于图像处理的焊接缺陷自动检测方法研究[D].江苏南京:南京航空航天大学,2013.
[4]梁鹏.X射线焊缝图像缺陷自动提取与识别技术研究[D].江苏南京:南京航空航天大学,2012.
[5]Shao J X,Du D,Shi H,et al.A fast and adaptive method for automatic defect detection in various real-time X-ray imaging systems[J].China Welding(English Edition),2012,21(1):8-12.
[6]云海姣,吴志勇.结合直方图均衡和模糊集理论的红外图像增强[J].计算机辅助设计与图形学学报,2015,27(8):1 499-1 505.
[7]陈莹,朱明.多子直方图均衡微光图像增强及FPGA实现[J].中国光学,2014,7(2):225-233.
[8]杨勇,黄淑英.一种改进的Pal和King模糊边缘检测算法[J].仪器仪表学报,2008,29(9):1 919-1 922.
[9]Theoharatos Ch,Economou G.Color edge detection using the minimal spanning tree[J].Pattern Recognition,2005,38(4):603-606.
[10]Otsu N.The shold selection method from gray-level histogram[J].IEEE Transactions on Systems,Man and Cybernetics,1979,9(1):62-66.
[11]Mehnert A,Jackway P.An improved seeded region growing algorithm[J].Pattern Recognition Letters,1997,18(10):1 065-1 071.
[12]刘奇琦,龚晓峰.一种二值图像连通区域标记的新方法[J].计算机工程与应用,2012,48(11):178-180.