医学图像增强算法与特征提取算法研究与实现  

Research and Realization of Enhancement Algorithm and Feature Extraction Algorithm for Medical Images

作　　者：李竹林[1] 王明芳[1] 呼建雪 白闪闪 

机构地区：[1]延安大学计算机学院,陕西延安716000

出　　处：《计算机技术与发展》2015年第1期115-118,共4页Computer Technology and Development

基　　金：国家大学生创新训练项目(201210719004);陕西省教育科研项目(2013JK1124)

摘　　要：医学图像质量是医生判读准确率高低的基础,医学图像增强是提高图像质量的重要方法。文中对医学图像的平滑处理方法和边缘特征提取算法进行了研究与实现,主要包括邻域平均法、加权平均法、中值滤波法、形态学增强处理、Canny边缘提取算子以及形态学提取边缘的方法。从模拟结果可以看出,经过增强处理后的图像以及所提取的边缘特征明显优于原图像。这样不仅可提高医生的判断速度和准确率,而且有助于对医学图像的特征描述、匹配、重建等工作。The quality of medical images is basis of judgments accuracy of doctors, and medical images enhancement is an important method to improve the quality of images. In this paper,the smooth processing algorithms and edge feature extraction algorithms are re-searched and realized for medical images,which mainly includes the neighborhood average method,weighted average method,median fil-tering method,morphological enhancement processing,Canny edge extraction operator and morphological edge extraction method. The simulation results show that the image quality and edge feature after enhancement processing is better than the original image obviously. This not only can improve the judgment speed and accuracy of the doctor,but also be helpful for features description,matching,recon-struction and so on.

关 键 词：噪声滤除 图像增强 梯度 形态学 边缘特征 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]