Joint Image Denoising Method Via Multiple Wavelet Bases

Wavelet analysis is an interesting research subject in the mathematic field. To discuss the new theory, methods and applications of wavelets are of great theoretical significance and practical value. At present, it has been widely used in many fields, such as signal analysis, image recognition, computer vision, data reduction, CT imaging, earthquake reconnaissance, and the analysis of atmosphere and sea. It is one of the most active application and research fields.In this paper, we discuss two parts in the view of the different effects to image denoising of different wavelet bases. The first part, we use Local-Bayes threshold and soft thresholding function to denoise the images. And the denoised result achieves the same performance with the undecimated wavelet denoising method, but its computation cost is much less than the former. The second part, we discuss the denoising results of the multiple wavelet bases, using wavelet decomposition combining the wiener filting. It regards the joint image denoising result via multiple wavelet bases as the pilot image, and then use it to and estimate the variance of the real image. So we can avoid the wavelet matching, and also achieve an apparently result.