二维经验模态分解法在漏磁图像处理中的应用

BEMD for Magnetic Flux Leakage Image Denoising

采用图像方法可以更加直观地对管道漏检测中的缺陷进行判断,但在图像数据的采集过程中噪声是不可避免的。采用二维经验模态分解(BEMD)与均值滤波法相结合的方法对漏磁图像进行去噪处理,将图像信号分解为有限个二维固有模态函数(BIMF)和一个残余分量,将残余分量保留,对BIMF分别进行均值滤波,再将处理后的BIMF分量与残差一起重构图像,所得重构图像在保留原图像基本信息的基础上,消除了大量噪声信息。文中还直接采用均值滤波方法对漏磁图像进行去噪处理,通过信噪比的比较,表明BEMD方法用于漏磁图像去噪效果明显。

Using the image method,the defects in the pipeline Magnetic Flux Leakage（MFL） can be more intuitively identified and inspected.However,the noise is inevitable in the process of data collection.In this paper,the bidimensional Empirical Mode Decomposition with mean filtering method was proposed for MFL image denoising.The MFL image was decomposed into a finite number of two-dimensional intrinsic mode function and a residual component by BEMD,the residual component was retained,and the mean filtering was used to remove the noise in the BIMF.Then the image was reconstructed which retained the basic information but removed the noise.The signal-to-noise ratio shows that the BEMD with mean filtering method for image denoising is better than the mean filtering method.