SAR Image Classification Using PCA and Texture Analysis
In Synthetic Aperture Radar (SAR) images, texture and intensity are two important parameters on the basis of which classification can be done. In this paper, 20 texture features are analyzed for SAR image classification into two classes like water and urban areas. Texture measures are extracted and then these textural features are further shortlisted using statistical approach, discriminative power distance and principal component analysis (PCA). In this study 30 SAR images are studied for 20 texture features. Finally, most effective 5 texture features are shortlisted for the classification of SAR images and accuracy is calculated by Specificity and Sensitivity test. The results obtained from test images give an accuracy of 95% for image classification.
KeywordsTexture analysis Classification SAR images PCA analysis
Unable to display preview. Download preview PDF.