基于传统图像处理的焊缝射线图像缺陷识别方法  

Defect recognition method of ray images of weld seams based on traditional image processing

作　　者：成志飞 张小刚 俞东宝[1] 汤慧[1] CHENG Zhifei;ZHANG Xiaogang;YU Dongbao;TANG Hui(China North Nuclear Fuel Co.,Ltd.,Baotou 014035,China)

机构地区：[1]中核北方核燃料元件有限公司,包头014035

出　　处：《无损检测》2025年第2期7-12,共6页Nondestructive Testing

摘　　要：核燃料元件焊缝中可能会出现气孔缺陷,严重影响产品的质量和安全性,为此设计了一种气孔缺陷检测方法,采用高斯滤波、形态学操作、边缘检测、轮廓拟合等方法提取了感兴趣区域,然后采用对比度拉伸、灰度值补偿、双边滤波、自适应阈值二值化等方法对检测图像进行识别。试验结果表明,所提方法实现了焊缝射线检测图像中气孔缺陷的识别,提高了缺陷检测的稳定性和准确性,同时也为处于明暗不均环境下的射线图像中的小尺寸近圆形等类似目标的检测提供了有效思路。Pore defects may occur in the welds of nuclear fuel elements,seriously affecting the quality and safety of the product.Therefore,a pore defect detection method was developed,which used Gaussian filtering,morphological operations,edge detection,contour fitting and other methods to extract the region of interest.Then,contrast stretching,grayscale compensation,bilateral filtering,adaptive threshold binarization and other methods were used to recognize the detection image.The experimental results showed that the proposed method achieved the recognition of porosity defects in weld seam radiographic images,improved the stability and accuracy of defect detection,and also provided an effective way to detect small-sized,nearly circular and similar targets in radiographic images in uneven light and dark environments.

关 键 词：图像处理 缺陷识别 边缘检测 轮廓拟合 

分 类 号：TP317[自动化与计算机技术—计算机软件与理论] TG115.28[自动化与计算机技术—计算机科学与技术]