摘要
提出一种改进的多参数小波阈值算法,通过调节因子k和r可以适应阈值λ的变化,与传统的硬阈值和软阈值法相比较,新算法去噪效果明显,尤其适用于去除强高斯噪声。以源图像和去噪后图像的峰值信噪比最大为依据,采用粒子群优化算法来选择自相应的调节参数,对新算法进行实验验证,仿真结果表明,新算法不仅可以有效去噪,而且可以避免高频信息的丢失从而可提高信噪比。
An improved multi-parameter wavelet threshold algorithm is proposed.It contains three parameters: the threshold value λ,adjustable factors k and r,which can be adjusted to the changes in the regulation of the threshold.Compared with the traditional hard threshold and soft threshold function for image de-noising,the proposed method has a significant effect,especially for the strong Gaussian noise.To validate this,an experiment is done with the method of particle swarm optimization(PSO) to select the threshold parameters according to the criterion of maximum peak signal to noise ratio(PSNR) between the original image and de-noised image.The simulation results show that,the improved algorithm can not only effectively remove the noise,especially for the strong Gaussian noise,but also can avoid the loss of high frequency useful information to improve the signal-to-noise ratio(SNR).Thus,the improved threshold algorithm has a significant effect on the de-noising for images with strong Gaussian noise.
出处
《西安邮电学院学报》
2011年第4期44-48,58,共6页
Journal of Xi'an Institute of Posts and Telecommunications
基金
Natural Science Research Fundation of Shaanxi Province (2009JM8004)
关键词
图像去噪
阈值
粒子群优化法
小波变换
强高斯噪声
image de-noising
threshold
PSO Algorithms
wavelet transform
strong Gaussian noise