SAR image segmentation via lattice filters based subband decomposition

In this paper, a new segmentation algorithm based on subband decomposition for SAR images is proposed. The decomposition of the SAR images into subband images is performed by low-pass and high-pass filters having lattice structure. Lattice filters are used in digital filter implementations because they have a number of interesting and important properties including modularity, low sensitivity to parameter quantization effects and a simple stability test. Two channel QMF (quadrature mirror filter) bank with lattice structure has perfect reconstruction property, while it guarantees good stop band attenuation for each of the analysis filters. The decomposition of the image into subbands is performed by row and column filtering of the image which corresponds to filtering by separable 2D filter. Features are extracted from the subband images. A minimum distance classifier is used in the classification step. Comparisons with wavelet transform based segmentation method are also included to show the effectiveness of the proposed method.