Code implementation of UESTC course project: Renwei Yang and YiKe Liu(co-first), 'A Two-stage Method for Non-extreme Value Salt-and-Pepper Noise Removal' [paper]
There are several previous methods based on neural network can have great performance in denoising salt and pepper noise. However, those methods work based on a hypothesis that the value of salt and pepper noise is exactly 0 and 255. It is not true in the real world. The result of those method deviation sharply when the value changes form 0 and 255. To overcome this weakness, our method aims at design a convolutional neural network to detect the noise pixels in a wider range of value and then a filter is used to modify it to 0 which is benefit for further work. And another convolutional neural network is used followed the filter to do the denoising and restoration work.
Corrupted, 20% SAP noise at non-extreme value
Stage1-Output, noise detection
Stage2-Output, PSNR = 39.07dB
Counterpart, without preprocessing, PSNR = 35.52dB
GT
