We provide a statistical analysis of the ability of digitized continuous shearlet systems to detect objects embedded in white noise. We analyze the possibility to subsample the shearlet transform and obtain a subset of significantly reduced cardinality that can still yield statistically optimal detection results.
@article{arxiv.1503.08565,
title = {Detection of Geometric Structures by an Optimally Subsampled Shearlet System in Noisy Digital Images},
author = {Philipp Petersen},
journal= {arXiv preprint arXiv:1503.08565},
year = {2015}
}