首页 | 本学科首页   官方微博 | 高级检索  
检索        

基于小波变换的数字胸片增强
引用本文:侯园园,周萍.基于小波变换的数字胸片增强[J].中国医学影像技术,2010,26(10):1976-1979.
作者姓名:侯园园  周萍
作者单位:首都医科大学生物医学工程学院计算机教研室,北京,100069
基金项目:首都医科大学基础临床合作基金 
摘    要:目的 研究一种基于小波变换的数字胸片图像增强新算法.方法 小波分解后,首先利用小波阈值法进行去噪预处理,然后对高频分量采用非线性增强,对低频分量采用反锐化掩模增强方法,通过小波反变换重构出增强后的图像.结果 通过对传统增强方法和本文提出的小波增强新方法进行实验对比,验证了本文算法对数字胸片图像有较好的增强效果.结论 对于分辨力低、噪声干扰严重、光照不均的数字胸片图像,本文提出的基于小波变换的增强新方法可保留图像细节信息,同时有效去除噪声.

关 键 词:X线影像增强  小波变换  反锐化掩模
收稿时间:2010/5/12 0:00:00
修稿时间:7/5/2010 12:00:00 AM

Approach on digital chest radiographs enhancement based on wavelet transform
HOU Yuan-yuan and ZHOU Ping.Approach on digital chest radiographs enhancement based on wavelet transform[J].Chinese Journal of Medical Imaging Technology,2010,26(10):1976-1979.
Authors:HOU Yuan-yuan and ZHOU Ping
Institution:Computer Teaching and Research Section, School of Biomedical Engineering, Capital Medical University, Beijing 100069, China;Computer Teaching and Research Section, School of Biomedical Engineering, Capital Medical University, Beijing 100069, China
Abstract:Objective To research a new approach on digital chest radiographs enhancement based on wavelet transform. Methods After wavelet decomposition, the wavelet threshold method was used to remove the noise. Then the nonlinear method was used to modify the high coefficients, the unsharp masking method was used for low coefficient. The enhanced images were obtained with inverse wavelet transform. Results Experiments were carried out on a digital chest radiograph based on several traditional enhancement methods. The results showed that this method had better enhancing effect than traditional approaches. Conclusion The wavelet transform enhancement method is suitable for the digital radiographs, which has weakness with lower contrast and some noises. It can not only retain image detail information, but also remove the noise effectively.
Keywords:Radiographic image enhancement  Wavelet transform  Unsharp masking
本文献已被 万方数据 等数据库收录!
点击此处可从《中国医学影像技术》浏览原始摘要信息
点击此处可从《中国医学影像技术》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号