Notes for Image Denoise

A survey paper from 1992–2002: To summarize, mainly from the spatial and fourier domain to wavelets domain, and use the probabilistic models to capture the relations between wavelet coefficients either intra or extra-scale. Mainly unsupervised traditional computer vision algorithms.

The most investigated domain in denoising using Wavelet Transform is the non-linear coefficient thresholding based methods. The procedure exploits sparsity property of the wavelet transform and the fact that the Wavelet Transform maps white noise in the signal domain to white noise in the transform domain. Thus, while signal energy becomes more concentrated into fewer coefficients in the transform domain, noise energy does not. It is this important principle that enables the separation of signal from noise.

Performance of denoising algorithms is measured using quantitative performance measures such as peak signal-to-noise ratio (PSNR), signal-to-noise ratio (SNR) as well as in terms of visual quality of the images. Many of the current techniques assume the noise model to be Gaussian. In reality, this assumption may not always hold true due to the varied nature and sources of noise.

Non-academic: Apps to do image denoise: super denoising

2002- 2014: focusing on different filtering and use new performance measure called The structural similarity index (SSIM).

Jain, Paras, and Vipin Tyagi. “A survey of edge-preserving image denoising methods.” Information Systems Frontiers 18.1 (2016): 159–170.

2014-present: Zhang, Kai, et al. “Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising.” IEEE Transactions on Image Processing 26.7 (2017): 3142–3155.

Code: