改进中值滤波和形态学的油管裂纹检测算法

The Pipeline's Crack Detection Algorithm Based on Improved Median Filtering and Morphology

油管裂纹检测是保证油管安全工作的前提。裂纹检测的难点是在检测到更多真实裂纹的同时尽可能的抑制噪声。因此,提出了一种改进的中值滤波和多角度形态学相结合的油管裂纹检测算法。首先,利用改进的中值滤波对图像进行去噪;然后,对图像进行小波分解,并用小波模极大值法处理高频分量,同时采用改进的形态学对低频分量进行裂纹检测;最后,将高低频裂纹整合,并将检测出的裂纹依据矩形度进行过滤。MATLAB实验结果显示,对比单独使用形态学法或小波模极大值法,上述算法能在较好抑制噪声的同时保证油管裂纹的连贯性,提高了检测效果。

The detection of pipeline crack is the prerequisite for safe work.The difficulty of crack detection is to detect more real cracks and suppress noise effectively.For this purpose,a new pipeline crack detection method combined median filtering and multi-angle morphological is proposed.Firstly,the median filtering algorithm was used to denoise the image.Secondly,the wavelet decomposition was applied to divide the image into two parts by frequency,then the wavelet modulus maxima method and improved morphology method were used to detect crack in high frequency components and low frequency components respectively.Finally,the high and low frequency cracks were integrated,and the crack that have been detected based on rectangle degrees was filtered.The MATLAB simulation resuits show that,compared with morphology method or wavelet modulus maxima method,this algorithm can suppress noise and ensure the continuity of the pipeline crack with high accuracy of crack detection.