使用希尔伯特-黄变换的医学图像检索  

Medical Image Retrieval Based on Hilbert-Huang Transform

作　　者：刘伟[1] 张宏[1] 周洁[1] 童勤业[1] 

机构地区：[1]浙江大学生物医学工程及仪器科学学院,杭州310027

出　　处：《传感技术学报》2007年第5期1077-1081,共5页Chinese Journal of Sensors and Actuators

基　　金：国家自然科学基金项目(30170267)

摘　　要：使用希尔伯特-黄变换对医学图像进行分解并将分解产生的内蕴模态函数及其二维希尔伯特变换的幅值作为纹理特征,提取后的特征用于医学图像检索.根据图像内局部极值点的几何分布,提出了一种新的基于聚类算法的边界处理方法.实验中使用的纹理特征包括基于希尔伯特-黄变换得到的特征和对比用的Gabor特征、纹理谱特征和多尺度复杂性及多尺度分维数特征.初步的实验结果表明:采用希尔伯特-黄变换可以有效地描述医学图像的纹理信息,并取得较好的图像检索结果.The approach of medical image decomposition and texture feature extraction based on Hilbert-Huang Trans- form（HHT）, which can decompose the image into a set of functions denoted Intrinsic Mode Functions（IMF） and a residue, was presented. The extracted features were used for medical image retrieval. The Bidimensional Empirical Mode Decomposition（BEMD） method was used to deconapose the medical image, the features extracted were the mean and standard deviation of the amplitude of the IMFs and their Hilbert transformations. Furthermore, according to the spatial relationship between local extrema points, a novel boundary processing approach based on clustering algorithm was proposed. In order to evaluate the proposed HHT-based feature, we also presented two multi-scale nonlinear texture features, which were multi-scale complexity and multi-scale fractal dimension feature. Preliminary comparision experimental results showed that the medical image retrieval results based on HHT were encouraged.

关 键 词：图像处理 医学图像检索 希尔伯特-黄变换 边界处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP751.1[自动化与计算机技术—计算机科学与技术]