<title>Flexible histograms: a multiresolution target discrimination model</title>

Abstract

ABSTRACT In previous work we have developed a methodology for texture recognition and synthesis that estimates and exploitsthe dependencies across scale that occur within images.2 In this paper we discuss the application of this techniqueto synthetic aperture radar (SAR) vehicle classification. Our approach measures characteristic cross-scale depen-dencies in training imagery; targets are recognized when these characteristic dependencies are detected. We presentclassification results over a large public database containing SAR images of vehicles. Classification performance iscompared to the Wright Patterson baseline classifier.3 These preliminary experiments indicate that this approachhas sufficient discrimination power to perform target detection/classification in SAR. 1. INTRODUCTION The detection and classification of targets in imagery is a difficult problem. Any successful algorithm must be ableto correctly classify the very wide range of images generated by a single target class. The sources of image variationsin SAR are many: target rotation, translation, articulation, sensor noise, depression angle, overlay, camouflage,and many others. Typically classifiers attempt to deal with these variations in one of two ways: invariance andduplication. For example, translation invariance could be achieved by only measuring the distance between detectedscatters, since distance is invariant to translation. However, such a method does not work as well as the targetrotates, since scatters may appear and then disappear. Alternatively, a duplicative technique could be used at the