改进的单尺度Retinex算法在管道焊缝图像中的应用  

Application of improved single-scale Retinex algorithm in pipeline weld image

作　　者：李翠 周瑞涛 王晓辉 邢军 Li Cui;Zhou Ruitao;Wang Xiaohui;Xing Jun(Qingdao Huanghai University,Qingdao Shandong,266555)

机构地区：[1]青岛黄海学院,山东青岛266555

出　　处：《电子测试》2021年第15期63-65,共3页Electronic Test

基　　金：青岛黄海学院博士科研启动基因项目(2016boshi04)。

摘　　要：管道焊缝质量是焊接工程质量评定中的重要一项,因此焊缝质量检测在焊接质量评定中具有重要的地位。为了有效追踪焊缝质量,提出一种改进的单尺度Retinex算法,对图像照度分量进行空域和频域低通滤波,并采用非线性变换函数调整反射分量的数据范围,来消除光照不匀对图像质量造成的影响。仿真实验结果表明,改进的单尺度Retinex算法处理效果优于SSR和多尺度Retinex算法(MSR),处理后的管道焊缝图像能够对焊缝内表面质量的判定提供很好的依据。Pipeline weld quality is an important item in welding engineering quality assessment,so weld quality inspection has an important position in welding quality assessment.In order to effectively track the weld quality,an improved single-scale Retinex algorithm is proposed,which performs low-pass filtering of the image illuminance components in the spatial and frequency domains,and uses a nonlinear transformation function to adjust the data range of the reflected components to eliminate uneven illumination The impact of quality.The simulation experiment results show that the improved single-scale Retinex algorithm is better than SSR and multi-scale Retinex(MSR).The processed pipeline weld image can provide a good basis for the judgment of the internal surface quality of the weld.

关 键 词：管道焊缝 RETINEX算法 低通滤波 非线性变换函数 

分 类 号：TG441.7[金属学及工艺—焊接] TP391.41[自动化与计算机技术—计算机应用技术]