Image Denoising Schemes Based on Discrete Wavelet Transform

摘要

In view of the fact that while signal energy becomes more concentrated into fewer coefficients in the wavelet transform domain, noise energy does not. We suggest the scheme of image denoising based on two-dimensional discrete wavelet transform. The denoising algorithm is described with some operators. By thresholding the wavelet transform coefficients of noisy images, the original image can be reconstructed correctly. Different threshold selection and thresholding methods are discussed. According to different behaviors of wavelet transform maxima of images and noise across different scales, a new adaptive local threshold scheme is proposed. Quantifying the performance of image denoising schemes by using the mean square error, we demonstrate the performance of the adaptive local threshold scheme, and compare it with the universal threshold scheme. The experiment shows that image denoising using the adaptive local threshold perform better than using the universal threshold.