Multiscale SAR Image Segmentation using Wavelet domain Hidden Markov Tree Models

We study the segmentation of SAR imagery using wavelet domain Hidden Markov Tree HMT models The HMT model is a tree structured probabilistic graph that captures the statistical properties of the wavelet transforms of images This technique has been successfully applied to the segmentation of natural texture images documents etc However SAR image segmentation poses a di cult challenge owing to the high levels of speckle noise present at ne scales We solve this problem using a truncated wavelet HMT model specially adapted to SAR images This variation is built using only the coarse scale wavelet coe cients When applied to SAR images this technique provides a reliable initial segmentation We then re ne the classi cation using a multiscale fusion technique which combines the classi cation information across scales from the initial segmentation to correct for misclassi cations We provide a fast algorithm and demonstrate its performance on MSTAR clutter data