Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding

摘要

This paper presents a novel image denoising framework using overcomplete topographic model. To adapt to the statistics of natural images, we impose both spareseness and topograpgic constraints on the denoising model. Based on the overcomplete topographic model, our denoising system improves the previous work on the following aspects: multi-category based sparse coding, adaptive learning, local normalization, lasso shrinkage function, and subset selection. A large number of simulations have been performed to show the performance of the modified model, demonstrating that the proposed model achieves better denoising performance.