Duman, KaanÇetin, A. Enis2016-02-082016-02-0820100277-786Xhttp://hdl.handle.net/11693/28472Conference name: Proceedings of SPIE, Algorithms for Synthetic Aperture Radar Imagery XVIIDate of Conference: 8–9 April 2010Target detection in SAR images using region covariance (RC) and codifference methods is shown to be accurate despite the high computational cost. The proposed method uses directional filters in order to decrease the search space. As a result the computational cost of the RC based algorithm significantly decreases. Images in MSTAR SAR database are first classified into several categories using directional filters (DFs). Target and clutter image features are extracted using RC and codifference methods in each class. The RC and codifference matrix features are compared using l 1 norm distance metric. Support vector machines which are trained using these matrices are also used in decision making. Simulation results are presented. © 2010 Copyright SPIE - The International Society for Optical Engineering.Englishdirectional filters (DFs)Synthetic aperture radar (SAR) imagesClutter imagesComputational costsDirectional filtersDistance metricsmatrixRegion covarianceSAR ImagesSearch spacesSimulation resultSynthetic aperture radar (SAR) imagesTarget detectionAlgorithmsAutomatic target recognitionDecision makingGearsImaging systemsRadar imagingSupport vector machinesSynthetic aperture radarSynthetic aperturesTracking radarRadar target recognitionConference Paper10.1117/12.850206