SAR Image Classification Using PCA and Texture Analysis

  • Mandeep Singh
  • Gunjit Kaur
Part of the Communications in Computer and Information Science book series (CCIS, volume 147)

Abstract

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.

Keywords

Texture analysis Classification SAR images PCA analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chamundeeswari, V.V., Singh, D., Singh, K.: An Analysis of Texture Measures in PCA-Based Unsupervised Classification of SAR Images. IEEE Geoscience and Remote Sensing Letters 6, 214–218 (2009)CrossRefGoogle Scholar
  2. 2.
    Unser, H.: Sum and difference histograms for texture classification. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(1), 118–125 (1986)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Clausi, D.A.: Comparison and fusion of co-occurrence, Gabor and MRF texture features for classification of SAR sea ice imagery. Atmos. Oceans 39(4), 183–194 (2001)CrossRefGoogle Scholar
  4. 4.
    Espinal, F., Jaweth, B.D., Kubota, T.: Wavelet based fractal signature analysis for automatic target recognition. Opt. Eng. 37(1), 166–174 (1988)CrossRefGoogle Scholar
  5. 5.
    Dekker, R.J.: Texture analysis and classification of ERS SAR images for map updating of urban areas in The Netherlands. IEEE Trans. Geosci. Remote Sens. 1(9), 1950–1958 (2003)CrossRefGoogle Scholar
  6. 6.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural Features for Image Classification. IEEE Transactions on Systems, Man and Cybernetics (3), 610–621 (1973)Google Scholar
  7. 7.
    Rangayyan, R.M.: Biomedical Image Analysis. CRC Press, Washington DC (2005)Google Scholar
  8. 8.
    Loh, H.H., Leu, J.G., Luo, R.C.: The Analysis of Natural Textures Using Run Length Features. IEEE Transactions on Industrial Electronics 2, 323–328 (1988)CrossRefGoogle Scholar
  9. 9.
    Galloway, M.M.: Texture Analysis Using Gray Level Run Lengths. Computer Graphics Image Processing 4, 172–179 (1975)CrossRefGoogle Scholar
  10. 10.
    Chu, A., Sehgal, C.M., Greenleaf, J.F.: Use of Gray Value Distribution of Run Lengths for Texture Analysis. Pattern Recognition Letter 11, 415–420 (1990)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mandeep Singh
    • 1
  • Gunjit Kaur
    • 2
  1. 1.Electrical and Instrumentation Engineering Dept.Thapar UniversityPatialaIndia
  2. 2.IBM India Pvt LtdPuneIndia

Personalised recommendations