摘要：Fluorescence microscopy imaging is a common biomedical tool for researchers make use in the study of active processes occurring inside live cells. Although fluorescent confocal microscopes are consistent instruments, the acquired images are normally corrupted by a severe type of poisson noise owing to the small amount of acquired radiation (low photon-count images) and also the huge opto-electronics amplification. These effects are still more destructive when very low intensity incident radiation is employed to avoid photo toxicity. To validate various standards of denoising algorithms to denoising the cardio fibroblast cells, in which all the fluorescence images are affected by Poisson Gaussian noise. These images are considered especially as a cardio fibroblasts contribute to structural, biochemical, mechanical and electrical properties of the myocardium. The denoising approaches employed here can directly act on Poisson noise like PURELET or use approaches wherein Gaussianize the noise by means of standard VST algorithms and then Gaussian denoising algorithms like BLS_GSM, BM3D and OWT SURELET are proposed. The experimental results are carried out on how the ISNR changes with the change in algorithms and inverse transforms for cardio fibroblasts.
