Three-Dimensional Wavelet Texture Feature Extraction and Classification for Multi/Hyperspectral Imagery

A 3-D wavelet-transform-based texture feature extraction algorithm for the classification of urban multi/hyperspectral imagery is investigated in this study. It is widely agreed that it is necessary to simultaneously exploit the spectral and spatial information for image classification. In this context, the 3-D discrete wavelet transform (3-D DWT) is studied since it considers the local imagery patch as a cube and, hence, is capable of representing the imagery information in both spectral and spatial domains. The notable characteristic of the 3-D DWT is the ability to decompose an image into a set of spectral-spatial components. Specifically, we propose three approaches for 3-D DWT texture extraction, namely, pixelwise, non-overlapping, and overlapping cube. Experiments conducted on AVIRIS hyperspectral and WorldView-2 multispectral images revealed that the 3-D DWT textures achieved much better results than the widely used spectral-spatial classification methods.