Objective Evaluation of Four SAR Image Segmentation Algorithms

摘要

Because of the large number of SAR images the Air Force generates and the dwindling number of available human analysts, automated methods must be developed. A key step towards automated SAR image analysis is image segmentation. There are many segmentation algorithms, but they have not been tested on a common set of images, and there are no standard test methods. This thesis evaluates four SAR image segmentation algorithms by running them on a common set of data and objectively comparing them to each other and to human segmentors. This objective comparison uses a multi-metric a approach with a set of master segmentations as ground truth. The metric results are compared to a Human Threshold, which defines performance of human se mentors compared to the master segmentations. Also, methods that use the multi-metrics to determine the best algorithm are developed. These methods show that of the four algorithms, Statistical Curve Evolution produces the best segmentations; however, none of the algorithms are superior to human segmentors. Thus, with the Human Threshold and Statistical Curve Evolution as benchmarks, this thesis establishes a new and practical framework for testing SAR image segmentation algorithms.