基于Contourlet变换的图像增强方法  

A Method for Image Enhancement Based on Contourlet Transform

作　　者：陈捷[1] 孙继银[1] 陈标[2] 许素芹[2] 

机构地区：[1]第二炮兵工程学院,陕西西安710025 [2]海军潜艇学院,山东青岛266071

出　　处：《微电子学与计算机》2007年第12期100-102,105,共4页Microelectronics & Computer

基　　金：国防"十一五"重点预研项目(513220208)

摘　　要：针对传统图像增强不能同时兼顾去噪和增强细节及小波变换在增强图像细节上的明显不足,提出一种了基于平移不变Contourlet变换的图像增强方法。采用平移不变Contourlet变换对图像进行多尺度分解,再利用非线性变换对Contourlet系数进行处理从而达到抑制噪声和增强细节的目的。实验结果表明本方法达到了良好的图像增强视觉效果,与传统的直方图均衡和小波域图像增强方法相比,其信噪比、(细节方差/背景方差)值都有了显著的提高。Since the conventional image enhancement methods can＇t restrain the noise while enhancing the image and the insufficiency in enhancing the details with wavelet transform in image enhancement, a new method for image enhancement based on translation invariance Contourlet is proposed. We use the invariance Contourlet to form the image representation and then deal with the Contourlet coefficients with nonlinear transform as to enhance the details and meanwhile restrain the noise. The experiment results show that this method achieve a good effect. The ratio of signal to noise, the ratio of detail variance to background variance are all increased comparing to the histogram equalization method and the wavelet transform image enhancement.

关 键 词：CONTOURLET变换 图像增强 平移不变 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]