Texture Segmentation of Sar Images Using the Wavelet Transform

Abstract

Multiresolution representation of an image using the wavelet transform is a new and effective approach for the analysis of image information content. The transform can be computed efficiently by a pyramidal algorithm based on convolutions with quadrature mirror filters. The result is a set of sub-band images which consists of a lower resolution version of the original image and a sequence of detail images containing higher spectral information. We used this representation for supervised texture segmentation of polarimetric SAR images acquired by the airborne JPL system. Since the transform generates localized spatial and spectral information simultaneously, texture segmentation can be accomplished by examining the spatial variations of the spectral sub-bands.