摘要
为了解决传统图像去噪算法仅对平稳噪声或缓慢变化噪声有效,且存在残留图像噪声较大的问题。研究了非平稳环境下基于小波变换的图像去噪算法。该算法根据图像与噪声在小波域的分布特性以及图像和噪声小波模极大值随尺度的变化大小不同,运用迭代算法得到不同尺度小波域中噪声的具体位置以及小波系数大小,完成了多尺度图像去噪。实验结果表明:对峰值信噪比较低的图像去噪,本方法去噪后峰值信噪比比传统的方法高,并且保留较多的图像细节。该算法对平稳和非平稳的噪声都能进行较好地去噪。
In order to solve the problem that the conventional algorithm of noise suppression is only efficient for stationary environments and has large level of image residual noise, a new algorithm for the noise reduction under non-stationary environments was put forward. Based on the different amplitude value change of image and noise and their distributing character in the wavelet domain, the algorithm can find the site and the value of the noise in the wavelet domain using the iterativeness algorithm. Experiments show that the PSNR reduction by the proposed algorithm is higher than that by conventional algorithm, and the high-frequency information of the image contains much after the noise suppression. The noise reduction by proposed algorithm is effective to reduce the noise under stationary and non-stationary environments.
出处
《四川大学学报(工程科学版)》
EI
CAS
CSCD
北大核心
2005年第1期99-103,共5页
Journal of Sichuan University (Engineering Science Edition)
关键词
图像
去噪
小波变换
非平稳性
Algorithms
Echo suppression
Iterative methods
Signal to noise ratio
Wavelet transforms