Accurate Single-Molecule Localization Of Superresolution Microscopy Images Using Multiscale Products

Recently, a class of single-molecule based localization techniques such as the Photo-activated Localization Microscopy(PALM) or the Stochastic Optical Reconstruction Microscopy (STORM) has ingeniously brought light-microscopy beyond the diffraction limit. However, as the single-molecule images contain point source objects (which have no clear edges, alignment and usually superimposed to the background), traditional restoration techniques used for industrial vision images do not give satisfactory result on the PALM/STORM dataset. In this work, we apply the multi-scale product of sub-band images resulting from the wavelet transformation, a technique originally used for astronomical image restoration, for the noise filtering and single-molecule detection in the Super-resolution images. This is an extension of the work by J.C Olivo-Marin(1) on spot detection in biological images. Experimental results on real and synthetic datasets with ground-truth show that our approach achieves very good detection rates as compared to the Quick PALM or the rapid STORM software.