摘要
针对总变分(TV)模型对图像的细节不敏感以及去噪的同时易造成边缘模糊的缺陷,提出了一种图像去噪的新算法。根据图像经过小波分解以后,细节主要集中在高频部分,而取相邻尺度的小波系数进行相关计算,可以提高边缘的定位精度。利用小波高频系数的相关计算来控制TV模型的扩散,在去噪的同时保护了边缘细节。仿真实验采用三种典型的离散方法,结果显示该算法处理的去噪图像视觉效果有所改善,且信噪比也有很大提高。
In order to overcome the weakness that edge information prone to blur of the Total Variation（TV） model while during the de-nosing procedure, a new algorithm is introduced base on the standard TV model. According to decomposition by wavelet, image details mainly concentrate in high frequency part, and make the correlation calculation between the adjacent wavelet coefficients that can increase the accuracy of edge. Wavelet coefficient’s correlation calculation is used for controlling the spread of TV model, the new model can de-noise as well as protect edge details. Three kinds of typically disperse methods are used in the simulation experiments, and the results show that this method can improve the visual effect and enhance the values of PSNR.
出处
《计算机工程与应用》
CSCD
2012年第31期175-178,共4页
Computer Engineering and Applications
