基于图像色彩信息的焊缝识别算法  

Image processing algorithm for weld seam recognition based on color analyzing

作　　者：邹怡蓉[1] 吴哲明[1] 郭桂林[1] 都东[1] 

机构地区：[1]清华大学先进成形制造教育部重点实验室,北京100084

出　　处：《焊接学报》2009年第10期37-40,共4页Transactions of The China Welding Institution

基　　金：国家自然科学基金资助项目(50628506)

摘　　要：提出了基于图像色彩信息的焊缝识别算法,旨在为用于自动化焊接及自动无损检测的焊缝跟踪技术探索可能的解决方案.从色彩理论和图像分割的基本原理出发,开展了对RGB(红、绿、蓝)彩色空间中图像色彩信息表达的研究,提出了彩色空间变换的方法,根据灰度直方图对图像进行阈值分割,得到焊缝区与母材区基本被区分开的二值化图像,进而检出焊缝边缘.结果表明,该算法简便易行,识别效果好.An algorithm of weld seam recognition based on color analyzing is proposed for automatic welding and automatic nondestructive test technologies.Based on color theory and the principles of image segmentation,the image representation in RGB(red,green and blue) color space is studied,and the method of color space transformation is proposed.The experiments demonstrate that the image described in the newly defined color space is able to be segmented by threshold value,which allows the seam region to be located and makes the algorithm and recognition easy.

关 键 词：图像色彩信息 RGB彩色空间 焊缝识别 图像处理 

分 类 号：TG409[金属学及工艺—焊接]