Removing Mixture of Gaussian and Impulse Noise by Patch-Based Weighted Means
This work addresses image denoising for applications like photography or medical imaging, but it is incremental as it builds on existing filters like non-local means and trilateral filters.
The authors tackled the problem of removing mixed Gaussian and impulse noise from images by proposing a patch-based weighted means filter, which demonstrated competitive performance compared to recent methods.
We first establish a law of large numbers and a convergence theorem in distribution to show the rate of convergence of the non-local means filter for removing Gaussian noise. We then introduce the notion of degree of similarity to measure the role of similarity for the non-local means filter. Based on the convergence theorems, we propose a patch-based weighted means filter for removing impulse noise and its mixture with Gaussian noise by combining the essential idea of the trilateral filter and that of the non-local means filter. Our experiments show that our filter is competitive compared to recently proposed methods.