Convolutional Neural Networks for Noise Classification and Denoising of Images

The goal of this paper is to find whether a convolutional neural network (CNN) performs better than the existing blind algorithms for image denoising, and, if yes, whether the noise statistics has an effect on the performance gap. For automatic identification of noise distribution, we used two different convolutional neural networks, VGG-16 and Inception-v3, and it was found that Inception-v3 identifies the noise distribution more accurately over a set of nine possible distributions, namely, Gaussian, log-normal, uniform, exponential, Poisson, salt and pepper, Rayleigh, speckle and Erlang. Next, for each of these noisy image sets, we compared the performance of FFDNet, a CNN based denoising method, with noise clinic, a blind denoising algorithm. It was found that CNN based denoising outperforms blind denoising in general, with an average improvement of 16% in peak signal to noise ratio (PSNR). The improvement is however very prominent for salt and pepper type noise with a PSNR difference of 72%, whereas for noise distributions such as Gaussian, FFDNet could achieve only a 2% improvement over noise clinic. The results indicate that for developing a CNN based optimum denoising platform, consideration of noise distribution is necessary.