基于改进小波变换的图像去噪与融合

Image denoising and fusion based on improved wavelet transform

为了提高图像去噪的质量,提出一种基于改进小波阈值的图像去噪和融合算法。首先利用小波阈值法和传统均值法对含噪图像进行去噪,得到两幅去噪图像;然后采用小波融合方法进行图像融合,得到最后的去噪图像。针对图像小波系数分布特点,低频系数采取加权能量融合算法,高频系数采取局部均值和局部标准差相结合的融合算法,尽可能保留图像的边缘纹理信息。为了验证该方法的有效性,与多种滤波方法进行比较,实验结果表明,在视觉效果和峰值信噪比定量指标上该方法去噪效果均优于单一小波去噪。

In order to improve the quality of image denoising,an image fusion and denoising algorithm based on improved wavelet threshold is proposed.Firstly,wavelet threshold method and traditional mean method are used to denoise the noisy image,and two denoised images are obtained;then wavelet fusion method is used for image fusion to obtain the final denoised image.According to the distribution characteristics of image wavelet coefficients,low frequency coefficients adopt weighted energy fusion algorithm,and high frequency coefficients adopt fusion algorithm combining local mean and local standard deviation,so as to retain the edge texture information of the image as much as possible.In order to verify the effectiveness of this method,compared with many filtering methods,the experimental results show that the denoising effect of this method is better than that of single wavelet denoising in terms of visual effect and quantitative index of PSNR.