Defect Extraction of ICT Images Based on Adaptive Morphological Filtering
-
摘要: 针对ICT图像缺陷现有提取方法的不足,提出了一种自适应的数学形态学滤波方法.该方法首先对整张图像进行分水岭变换,根据区域大小自适应地选取结构元素区域.然后对该区域边界进行椭圆拟合,以确定结构元素模板.根据形态学原理运用此模板对图像进行闭运算,从而获得图像背景.最后,用背景图像减去原始图像,即可获得缺陷的图像.试验结果表明,该方法能获得更好的图像缺陷提取效果.Abstract: To overcome the shortcomings of the current defect extraction methods for ICT(industrial computerized tomography) images,an adaptive filtering method based on the mathematical morphology was proposed.Firstly,with this method,the primary region of a structural element is automatically chosen in the light of region size after the watershed transformation of full ICT images.Secondly,the ellipse fitting operation is applied to the boundary of the primary region to get the final structural element.Then the background images are gotten by the closing operation of the mathematical morphology on the original images using the final structural element.Finally,the defect images are obtained by subtracting the original image from the background images.The experimental results show that compared with the current methods,the proposed method can obtain a good result of defect extraction of ICT images.
-
孙怡,孙洪雨,白鹏,等.射线焊缝图像中缺陷的实时检测方法[J].焊接学报,2004,25(2):115-123.SUN Yi,SUN Hongyu,BAI Peng,et al.Real-time automatic detection of weld defects in X-ray images[J].Transactions of The China Welding Institution,2004,25(2):115-123.[2] VINCENT L,SOILLE P.Watersheds in digital spaces:an efficient algorithm based on immersion simulation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.[3] 刚铁,王东华.基于自适应形态学滤波的X射线图像的缺陷提取[J].机械工程学报,2001,37(5):85-89.GANG Tie,WANG Donghua.Defect extraction of X-ray images based on adaptive morphology faltering[J].Chinese Journal of Mechanical Engineering,2001,37(5):85-89.[4] 周正干,赵胜,安振刚.航空发动机叶片实时成像自动检测技术研究[J].机械工程学报,2005,41(4):180-184.ZHOU Zhenggan,ZHAO Sheng,AN Zhengang.Research on automatic inspection techniques of real-time radiography for turbine-blade[J].Chinese Journal of Mechanical Engineering,2005,41(4):180-184.[5] 罗爱民,殷国富,魏万迎,等.基于Hauedorff距离区域生长的缺陷边缘重建方法[J].机械工程学报,2007,43(4):132-137.LUO Aimin,YIN Guofu,WEI Wanting,et al.Method of defect edge reconstruction based on region growing algorithm and the HAUSDORFF distance[J].Chinese Journal of Mechanical Engineering,2007,43(4):132-137.[6] 冈萨雷斯,伍德.数字图像处理[M].阮秋琦,阮宇智,译.北京:电子工业出版社,2003:420-460.[7] MEYER F.Topographic distance and watershed lines[J].Signal Processing,1994,38(1):113-125.[8] 王静.产品层析图像的轮廓匹配技术研究[D].西安:西北工业大学,2001.
点击查看大图
计量
- 文章访问数: 1688
- HTML全文浏览量: 70
- PDF下载量: 511
- 被引次数: 0