基于Contourlet变换的带噪图像增强方法  

Noisy Image Enhancement Algorithm Based on the Contourlet Transform

作　　者：董鸿燕[1] 李吉成[1] 沈振康[1] 

机构地区：[1]国防科技大学 ATR 重点实验室,湖南长沙410073

出　　处：《信号处理》2007年第6期836-840,共5页Journal of Signal Processing

基　　金：武器装备预研基金项目(编号:51483020105ZS9309)

摘　　要：为了解决带噪图像增强中抑制噪声和增强边缘细节的矛盾,提出一种基于Contourlet变换的带噪图像增强方法。Contourlet变换具有多分辨率、局部定位性、多方向、各向异性等特点,比小波变换更能有效地捕获图像中的高维奇异性。根据这一特点,本文综合考虑变换后系数尺度间和尺度内的依赖性,先在Contourlet变换域中设置自适应阈值抑制噪声;在此基础上,应用广义非线性增益函数来提高较弱细节的局部对比度。实验结果表明,该算法较好的抑制噪声,增强图像细节对比度。A new image enhancement method aimed at optimizing contrast of image features while minimizing image noise is proposed in the paper based on the Contourlet transform. Contourlet transform is is multiresolutional, localized, muhidirectional and anisotropic, so it is more effectively capture high dimensional singularity. Because of all these characteristics, and considering of the intrasubband and interscale dependencies ,firstly an adaptive shrinkage denoising is accomplished. Then the generalized nonlinear adaptive agin function is used to enhance the features with low contrast while protecting the strong contrast features from over enhancing. Results of experiments show that this method enhance the contrast of the image while avoiding over-enhancement of noise.

关 键 词：图像增强 CONTOURLET变换 多方向 多尺度 广义非线性增益 

分 类 号：TN911[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]