一种基于二维离散小波变换的医学图像增强算法  

A Medical Image Enhancement method Based on Two-dimensional Discrete Wavelet Transform

作　　者：侯艳芹[1] 李均利[1] 魏平[2] 陈刚[1] 

机构地区：[1]宁波大学数字技术与应用软件研究所,宁波315211 [2]浙江大学计算机学院,杭州310027

出　　处：《计算机工程与应用》2006年第7期227-229,共3页Computer Engineering and Applications

基　　金：国家自然科学基金资助项目(编号:60302012);宁波市科技攻关项目(编号:2005B100016)

摘　　要：噪声是影响医学图像质量的最重要的因素之一。去除噪声,增强图像以提高图像质量是医学图像处理的重要课题。传统的图像增强方法在改善图像视觉效果的同时还存在噪声过增强问题,不适于医学图像增强。针对这种情况,文章提出了基于二维离散小波变换的医学图像增强算法。在多尺度分析基础上,该算法对小波分解得到的低频子带图像采用两步提升法进行对比度增强处理,而对小波分解得到的不同方向上的小波系数进行不同程度的去噪并增强。实验结果表明,该方法在提高医学图像对比度改善图像质量的同时有效地解决了传统算法中难以克服的噪声放大问题。处理后的图像更利于医生进行分析诊断和医学影像的后续处理。Noise is one of the most important factors,which affects the medical image quality.Removing noise and enhancing image to improve the quality of image is the important item of medical image processing.Conventional image enhancement algorithms not only can improve the visual quality of image but also have shortcoming of noise over- enhancement.They are not suitable carrying on medical image processing.In order to solve this problem,this paper proposes a medical image enhancement based on two-dimensional discrete wavelet transform.On the basis of taking full advantage of multi scale wavelet analysis,the proposed algorithm improves the contrast of the approximations of the wavelet transform through two lifting steps ,and shrinkages the coefficients of wavelet transform on the different degree and then enhances the coefficients.The results of experiment show that the proposed algorithm can raise the contrast of image and improve the quality of image,and resolve the problem of the noise magnified,which is hard to process in the conventional algorithms.The handled image is advantageous to the doctor to carry on analysis and follow-up processing of medical images.

关 键 词：小波变换 医学图像增强 多尺度分析 

分 类 号：TN919.81[电子电信—通信与信息系统]