基于Dual-Tree CWT和自适应双边滤波器的图像去噪算法

Image denoising algorithm based on Dual-Tree CWT and adaptive bilateral filtering

针对目前图像去噪方法主要局限于单一噪声,无法有效解决多种混合噪声的不足,提出了一种基于DualTree CWT和自适应双边滤波器的图像去噪算法。该算法使用双树复小波变换对含噪图像进行多尺度和多方向的分解,由改进阈值对各个方向子带的高频系数进行阈值量化,同时由自适应双边滤波对每尺度下低频子带系数进行滤波,并将重构得到的图像进一步去除噪声。实验仿真结果表明,该方法对混合噪声的滤除效果明显优于现有算法,且能较好地保护图像的边缘细节信息,通过客观评价指标峰值信噪比(PSNR)和均方根误差(RMSE)定量比较,PSNR提升了5.333 2~6.527 8 d B,RMSE可降低29.41%~46.03%,运行时间仅为1.492 0 s,整体降噪性能更优。

For the current image denoising methods are mainly limited to the single noise,can not effectively solve the lack of the various mixed noise,an image denoising algorithm based on Dual-tree CWT and adaptive bilateral filtering is proposed.The algorithm uses the Dual-tree CWT to decompose the noisy image in multi-scales and multi-directions.The high-frequency coefficients of the sub-bands in each direction are quantized by the improved threshold,the low-frequency sub-band coefficients are filtered simultaneously by the adaptive bilateral filtering in each scale,and the reconstructed image is further removed.Experimental results show that the proposed method is superior to the existing algorithms,and can better protect edge detail information of the image.Through the quantitative comparison of the Peak Signal-to-Noise Ratio(PSNR)and the Root Mean Square Error(RMSE)of the objective evaluation index,PSNR can be improved by 5.333 2-6.527 8 dB,RMSE can be reduced up to 29.41%-46.03%,the running time is only 1.492 0 s,the overall noise reduction performance is more excellent.