Image Denoise and Enhancement Based on Structure Self-similarity in Wavelet Domain
Huantong Geng · 2010
Image denoise is a very important problem in image quality enhancement.For the image noises are different from each other,it is difficult to select one best denoise algorithm for all images which are degraded by different kinds of noises.In the paper,a novel algorithm based on wavelet transform and structure self-similarity was introduced,which is effective to confine the random noise.Beside the properties of time frequency localization and multi-resolution of wavelets,the self-similarity of image were used.It first separated the image into several blocks equally based on the self-similarity.And then,wavelet transform coefficients were used to enhance edge information.At the same time,image noises were confined.Experiment results show the excellent effect of the algorithm.