Loading...
Automatic SAR segmentation by fuzzy hit-or-miss and homogeneity index
Author(s)
Date Issued
December 1, 2005
Type
Conference Paper
Abstract
Object-based segmentation is the first essential step for image processing applications. Recently, segmentation techniques have been developed, but not enough to preserve the significant information contained in the small regions of an image. The proposed method is to partition an image into homogeneous regions by using a fuzzy hitor- miss operator with an inherent spatial transformation, which endows to preserve the small regions. In the proposed scheme, an iterative segmentation technique is formulated as consequential processes. Then, each time in iterating, hypothesis testing is used to evaluate the quality of the segmented regions with a homogeneity index. Our method is unsupervised and uses few parameters, most of which can be calculated from input data. This comparative study indicates that the new iterative segmentation algorithm provides acceptable results as seen in the tested examples of synthetic aperture radar (SAR) images. © 2005 by the American Society for Photogrammetry and Remote Sensing.
Citation
American Society for Photogrammetry and Remote Sensing Annual Conference 2005 Geospatial Goes Global from Your Neighborhood to the Whole Planet, 1, 440-451, 2005