Application of Poisson Image Denoising by ICA to Penumbral Imaging

This paper proposes a new method based on independent component analysis (ICA) for Poisson noise reduction. In the proposed method, the image is first transformed to ICA domain and then the noise components are removed by a soft thresholding (Shrinkage). The proposed method, which is used as a preprocessing of the reconstruction, has been successfully applied to penumbral imaging. Both simulation results and experimental results show that the reconstructed image is dramatically improved in comparison to that without the noise-removing filters.