Mixed Gaussian-Impulse Noise Reduction from Images Using Convolutional Neural Network

Abstract

The removal of mixed-noise is an ill-posed problem due to high level of non-linearity in the distribution of noise. Most commonly encountered mixed-noise is the combination of additive white Gaussian noise (AWGN) and impulse noise (IN) that have contrasting characteristics. A number of methods from the cascade of IN and AWGN reduction to the state-of-the-art sparse representation have been reported to reduce this common form of mixed-noise. In this paper, a new learning-based algorithm using the convolutional neural network (CNN) model is proposed to reduce the mixed Gaussian-impulse noise from images. The proposed CNN model learns the end-to-end mapping from noisy image to noise-free image. The model has a small structure yet is capable of providing superior performance as compared to the well established methods. Experimental results show that the proposed CNN-based denoising method performs better than the sparse representation and patch-based methods. Moreover, due to the lightweight structure, the denoising operation of the proposed CNN method is computationally faster than that of the established methods.

Publication
In To Appear
Date
Links