TerraSAR-X Image Analysis using PCA, ICA and SVM
Houda Chaabouni-Chouayakh, David Mata‐Moya, Mihai P. Datcu · elib (German Aerospace Center) · 2008
Recognizing scenes using high resolution Synthetic Aperture Radar (SAR) images requires the capability to identify relevant signal signatures, depending on variable image acquisition geometry, arbitrary objects poses and configurations. This paper addresses a target recognition problem in high resolution SAR images using Principal Components Analysis (PCA), Independent Components Analysis (ICA), as well as a combination of both, for feature extraction; and Support Vector Machine (SVM) for classification. The performance of these techniques were analyzed and tested on a four-class database collected from the same TerraSAR-X High Resolution spotlight Mode (HS), Multi Look Ground Range Detected (MGD) image, over the Pyramids of Gizeh in Egypt.