基于随机共振和维纳滤波的图像复原技术研究  

The Research of Image Restoration Based on Stochastic Resonance and Wiener Filtering

作　　者：姜源[1] 彭月平[1] 王剑[1] 

机构地区：[1]武警工程大学,西安710086

出　　处：《科学技术与工程》2016年第8期223-228,共6页Science Technology and Engineering

基　　金：国家博士后基金面上项目(2013M542355);武警工程大学基础研究项目(XJY201420)资助

摘　　要：随机共振不同于维纳滤波等传统信号处理方法,在非线性系统作用下,能利用噪声实现对强噪声背景下弱信号的处理。考虑到随机共振与维纳滤波算法的优势和不足,提出和实现了基于双稳态随机共振与维纳滤波的图像自适应复原增强算法;该算法在利用行列扫描对图像进行降维的基础上,引入拉伸变换提升图像质量;并经维纳滤波进行优化处理。仿真结果和实际应用表明:所提算法具有很好的鲁棒性,无论是复原低信噪比信号还是高信噪比信号,复原效果都优于维纳滤波和小波变换等传统复原算法和基于双稳态系统复原算法。在噪声滤除及提升图像对比度和清晰度上具有更好效果,特别是在复原被强噪声污染的信号,即信噪比很低的信号时,所提算法抑制噪声能力更强,复原效果更好。该算法克服了随机共振处理高信噪比信号效果不佳和鲁棒性差等问题,在弱信号提取,特别是强噪声和暗环境下的图像处理方面具有一定的应用前景。Stochastic resonance is different from the traditional signal processing method such as the Wiener filtering,which uses the noise to process the weak signal in the nonlinear system under strong noise. Considering that the stochastic resonance and the traditional algorithm have their own advantages and disadvantages,this paper proposes and realizes a image restoration algorithm based on the combination of the bistable stochastic resonance system and the Wiener filtering algorithm. In this algorithm,the image is using the line-rank scanning to realize dimensionality reduction,and the image quality is enhanced by scaling transform before,and then the processing is optimized by the Wiener filtering. The simulation results and practical application show that the proposed algorithm has good robustness,and the algorithm has better performance than the traditional restoration algorithms such as the Wiener filtering and wavelet transform. The algorithm has better effect on the noise filtering and image contrast and resolution enhancing,especially in the recovery of the signal with strong noise pollution,the result of this algorithm to filter noise and image restoration becomes more better. The algorithm overcomes the problem of high SNR signal processing and poor robustness,and has a certain application prospect in weak signal extraction,especially in strong noise and dark environment.

关 键 词：随机共振 双稳态系统 弱信号 维纳滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]