焊缝射线检测图像的缺陷搜寻与算法优化

Flaws finding and algorithm optimization of radiographic inspection of welding bead

基于X射线成像的焊缝缺陷自动检测技术对提高工业射线检测的自动化水平具有重要意义。在通过图像处理算法进行焊接缺陷提取的过程中,存在各种干扰,要求算法有很强的抗干扰能力。尝试了均值滤波背景相减和底帽变换两种缺陷提取算法,并分析存在的主要问题。针对这些问题,提出相应的解决办法,即模板优化算法和多特征再筛选算法,有效地解决了缺陷误检和漏检之间的矛盾。

The automatic inspection technique of weld defects based on X ray imaging is of great importance to improve the automation level of industrial radiographic inspection. In the process of extracting welding defects through image processing algorithms ,there are many kinds of interference,which requires the algorithm to have strong anti-interference ability. Two kinds of defect extraction algorithms ,mean filtering, background subtraction and bottom hat transformation,are discussed and the main problems are analyzed. In view of these problems,tile corresponding solutions are proposed,namely template optimization algorithm and multi feature re screening algorithm,which effectively solves the contradiction between defect detection and missed detection.