摘要
提出一种基于Contourlet变换域的图像滤噪算法,对带噪图像进行多尺度、多方向的Contourlet分解,依据Contourlet变换域系数的估计损失期望最小化准则,在Contourlet域中得到各子带内邻域系数的滤噪最优阈值与最优窗口尺寸,利用Contourlet变换域系数的萎缩实现滤噪。仿真结果表明,与现有的Contourlet变换域图像滤噪算法相比,该算法能有效保护图像的细节和纹理,具有较好的视觉效果和较高的峰值信噪比。
This paper proposes a novel image denoising algorithm based on Contourlet domain. By using Contourlet transform, the noised image is decomposed into a low frequency subband and a set of multiscale and multidirectional high frequency subbands. Optimal thresholds and neighbouring window sizes for each subband arc determined by minimizing the loss expectation of estimating Contourlet coefficients and image denoising is implemented via shrinkage of Contourlet coefficients. Simulation results show the superiority of the proposed method in den＇oising noise and preserving texture details compared with the existing methods and the proposed method yields better visual effect and higher PSNR as a result of considering dependencies of Contourlct neighborhood coefficients.
出处
《计算机工程》
CAS
CSCD
北大核心
2010年第5期223-224,227,共3页
Computer Engineering
基金
陕西省自然科学基金资助项目(2009JM8003)
陕西师范大学研究生培养创新基金资助项目(2009CXS025)
作者简介
作者简介：王晅（1966-），男，副教授、博士，主研方向：图像处理，模式识别；
张小景，硕士研究生；
马进明，副研究员、硕士
