一种边缘保持的医学图像去噪方法  

Edges Preserving Method for Medical Image Denoising

作　　者：秦绪佳[1,2] 张素琼[1] 刘世双[1] 徐晓刚[3] 

机构地区：[1]浙江工业大学软件学院,杭州310032 [2]浙江大学CAD&CG国家重点实验室,杭州310027 [3]大连舰艇学院装备系统与自动化系,大连116018

出　　处：《计算机科学》2009年第11期279-282,共4页Computer Science

基　　金：国家自然科学基金(60673063;60873033);国家863计划项目(2007AA12Z141);浙江省自然科学基金(Y1080436);浙江大学CAD&CG国家重点实验室开放课题资助

摘　　要：医学图像去噪在图像处理中占有重要地位,对获取的医学图像进行去噪是进一步分析和计算的基础。将一维经验模式分解方法扩展到二维,提出了基于二维经验模式分解的医学图像边缘保持去噪方法。该方法先将图像进行经验模式分解,得到内蕴模式分量IMF和剩余分量,图像的噪声及边缘信息主要集中在IMF中;然后再将IMF进行经验模式分解,得到IMF的高频分量和剩余分量;最后将两次分解的剩余分量叠加,得到边缘保持的去噪图像。实验结果表明,处理后的图像较传统的医学图像去噪方法有明显的改善,在有效去噪的同时增强了边缘保护的能力。Image denoising plays an important part in medical image processing,denoising the medical images is the basis for further analysis and calculations. To extend the one-dimensional EMD method to two-dimensional, a novel edges preserved image denoising method for medical images based 2D EMD was proposed. Firstly, decomposed the image by EMD, and the intrinsic mode function（IMF） and the remaining component of the image were obtained. Image noises and edges information are focus on the IMF. Secondary, decomposed the IMF into high frequency component and the remaining component by EMD. Finally, added the two remaining components, the edges preserved denoise image was obtained. Experiments show that the proposed method can remove noises in the image and keep image edges information.

关 键 词：医学图像 图像去噪 经验模式分解 边缘保持 熵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]