An automatic and parameter-free information-based method for sparse representation in wavelet bases.

In this article an information-based method for the selection of expansion coefficients of functions in a Hilbert basis is presented. An information-based measure, namely Entropic NID (ENID), is presented; the optimal separation point between more informative coefficients and less informative ones is selected by evaluating the information contribution of two competing sets of expansion coefficients. A consistent numerical scheme is given to approximate ENID and the numerical error is studied. Numerical simulations are provided to test the behaviour of ENID in different wavelet bases, as well as to perform comparative studies. • Sparse representation is achieved in wavelet bases. • Absolute value of differential entropy of a function is a measure of complexity. • An information measure based on Normalized Information Distance is proposed. • Optimum coefficients set is related via experiments to Vitanyi's NCD. [ABSTRACT FROM AUTHOR]