Bilateral Filter Approach and Fast Discrete Curvelet Transform for Poisson Noise Removal from Images
Sajil Daniel John, Jilu George · 2013
We analyse two methods of removing poisson noise from images using a bilateral filter and by Fast discrete Curvelet Transform (FDCT). The Variance stabilizing transform (VST) is the main feature of the noise removal as it converts the Poisson distribution to the Gaussian domain, which makes the noise removal process relatively simple. Once the Gaussian distribution is obtained, the bilateral filter (BF) can be used for removing noise. We can also use the FDCT instead of bilateral filter, as it is capable of sparse representation of image intrinsic features. We implement both the methods separately, compare them and demonstrate simulations for monitoring their effectiveness in poisson noise removal. The results show that FDCT is more efficient for preserving image features, while bilateral filter is much faster and simple to implement.