Data Analytic Wavelet Threshold Selection in 2D Signal De-noising

A data adaptive scheme for selecting thresholds for wavelet shrinkage-based noise removal is developed. The method involves a statistical test of hypotheses based on a two-dimensional cumulative sum of wavelet coefficients, which takes into account the coefficients' magnitudes and their relative positions. The amount of smoothing performed during noise removal is controlled by ff, the usersupplied confidence level of the tests. Simulated critical points for the statistical test are tabulated for a wide range of signal sizes and confidence levels. Results are shown which indicate the scheme performs well on a variety of signals. Keywords--- Noise removal, wavelet shrinkage, Brownian sheet stochastic process I. Introduction Wavelet shrinkage has recently emerged as a powerful tool for extracting signals from noisy data [1]. A fundamental issue in wavelet shrinkage signal de-noising is the choice of the shrinkage threshold . Many data-dependent threshold selection techniques in statist..