Beamlet-based Linear Feature Detection Algorithm for Welding Image Processing
Weld seam images are replete with noise due to welding arc,heat and splatters,and ordinary line detection algorithms such as Hough Transform is not an ideal approach to extract significant linear features from it. In this paper.we present a novel Iine detection algorithm based on beamlet analysis.a new multiscale image analysis theory defined by David L.Donoho.The algorithm is described in detail after introducing the beamlet dictionary and beamlet transforilL Talking into account of some special characteristics of welding image processing,we add an orientation-thresholding step to the standard beamlet-based line detection algorithm.Experiments are conducted to detect linear features in noisy weld seam images at different scales and to test the anti-noising performance of our algorithm.The result of experiments show that our algorithm is characterized bV its high efficiency and its prominent anti-noising performance.and is very suitable for detecting linear features in highly noisy weld seam images.The orientation threshold can not only reduce the caiculation Ioad.expedite its running speed.but also.t can help to improve the anti.noising performance of the standard beamlet-based linedetection algorithm.
Beamlet Transform Line Detection Image Processing Weld Seam
DENG Shuangcheng JIANG Lipei XUE Long JIAO Xiangdong
国际会议
The International Conference Information Computing and Automation(2007国际信息计算与自动化会议)
成都
英文
732-736
2007-12-19（万方平台首次上网日期，不代表论文的发表时间）