中文摘要：

针对钢管缺陷的X射线检测方法,目前主要采用对数字式X射线（DR）影像进行人工判读的方式来检测缺陷,该方法受主观因素影响大,工作强度高,效率低。为替代人工检视方法,依据DR影像特征,研究了基于数字图像处理的缺陷检测算法。实验结果表明,采用的算法具有良好的适应性,比传统方法检测出的细小缺陷的效率更高,可满足对缺陷进行在线监测的需求。

英文摘要：

At present,we mainly rely on manual interpretation on digital radiography（DR）images to detect the defects for steel tube X-ray detection techniques.This method is easily affected by the subjectivity of the observer,and has excessive labor work and low efficiency.To substitute manual interpretation,according to the characteristics of DR images,this paper studies the steel tube defects detecting algorithm based on digital images processing.Experimental results show that,the algorithm introduced in this paper has good adaptability and have an advantage over manual interpretation in detecting tiny defects and detection efficiency,which satisfying the requirement to detect defects in real time.