The Stochastic Matched Filter and Its Applications to Detection and De-Noising
Philippe Courmontagne · Sciyo eBooks · 2010
This chapter concerned the problem of a noise-corrupted signal expansion and its applications to detection and signal enhancement. The random signal expansion, used here, is the stochastic matched filtering technique. Such a filtering approach is based on the noisy data projection onto a basis of known vectors, with uncorrelated random variables as decomposition coefficients. The basis vectors are chosen such as to maximize the signal to noise ratio after denoising. Several experiments in the fields of short signal detection in a noisy environment and of signals de-noising have shown the efficiency of the proposed expansion, even for unfavorable signal to noise ratio.