摘要
详细论述了各向异性扩散的PDE(偏微分方程)降噪算法原理,提出一种各向异性扩散的PDE降噪和分水岭算法相结合的脑MRI医学图像分割算法。采用各向异性扩散的PDE降低原始图像噪声,然后利用形态学算法对降噪后的图像进行形态学处理,通过形态学知识提取图像边界。利用图像的几何特征,去除非目标区域,再采用分水岭变换进行图像分割,并通过脑MRI图像验证了此方法的优势。实验结果进一步验证了其可行性。
In this paper discusses principles of the algorithm of the anisotropic diffusion PDE(partial differential equation) noise reduction.An image segmentation algorithm proposed of the anisotropic diffusion PDE noise reduction and watershed algorithm combining.First,that original image reduces noise by the anisotropic diffusion PDE;secondly,that use algorithms of morphological processing image of noise reduction after;finally,that extracted image boundary by morphological knowledge.We use geometric features of the image,and remove non—target area,and using watershed transformation segmentation of the image,and verify the advantages of the method by MRI image of brain.The results further validate the feasibility
引文
[1]杨迎春.基于偏微分方程的图像去噪算法研究[D].太原:中北大学,2012.
[2]高飞.基于偏微分方程的图像去噪算法研究[D].大连:大连海事大学,2011.
[3]陈小晴.基于偏微分方程的图像去噪方法研究[D].南京:南京信息工程大学,2013.
[4]于海燕.基于偏微分方程的图像处理方法及其在生物医学中的应用[D].哈尔滨:哈尔滨工业大学,2010.
[5]Tasdizen T.Whitaker R.Anisotropic diffusion of surface normal for feature preserving surface reconstruction[J].Proceedings of 4th International Conference on 3-D Digital Image and Modeling,Banff,2003:353-360.
[6]YOU Y L,KAVEH M.Fourth-order Partial Differential Equations for Noise Removal[J].IEEE Trans on Image Processing,2000,9(10):1723-1729.
[7]Bieniek A,Moga A.An efficient watershed algorithm based on connects components[J].Pattern Recognition,2000(3):907-716.
[8]HIEU T,MARCEL M,REIN V.Water snakes:Energy driven watershed segmentation[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(3):330-342.
[9]陈婷婷.采用模糊形态学和分水岭算法的图像分割研究[D].重庆:西南大学,2008.