LS2W: Implementing the Locally Stationary 2D Wavelet Process Approach in R

Abstract

Locally stationary process representations have recently been proposed and applied to both time series and image analysis applications. This article describes an implementation of the locally stationary two-dimensional wavelet process approach in R. This package permits construction of estimates of spatially localized spectra and localized autocovariance which can be used to characterize structure within images.

Keywords

• random field
• locally stationary
• local autocovariance
• LS2W
• texture analysis
• non-decimated wavelets
• R