Deep Learning Based Image Denoising Algorithm

Image denoising is one of the basic problems in image processing. Last decade,current image denoising algorithms have been able to achieve quite good performance when the noise is weak. However, when the noise level is high, due to the low signal to noise ratio and the lack of useful information in the given image, the performance of these algorithms decreases rapidly.Neural networks are very suitable for the image denoising problem in high noise level by learning statistical properties of natural images. However, recent studies on deep learning have shown that neural networks based on the traditional sigmoid function have its own limitations which limit its performance.In this paper, based on the tool of neural networks, we investigate the setting of the networks and the training procedure according to properties of the image denoising problem. We then propose to adopt the rectifier linear(ReL) function instead of the Sigmoid function as the activation function of hidden layers to further enhance the ability of neural network on solving image denoising problem. Our experiments show that by better capturing patterns in natural images, our model can achieve better performance and less time consumption than those using sigmoid units. In comparison with other existing methods, our approach achieves very competitive result especially in high noise level, which reserves image details well when removing noise.