ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa


Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2014, Vol. 11, No. 1, pp. 301-307

One channel TerraSAR-X image textural RGB segmentation

N.V. Rodionova1 
1 V.A. Kotelnikov Institute of Radioengineering and Electronics RAS, Fryazino, Russia
One of the major steps in image processing is segmentation, or splitting the image into areas uniform in some signatures. As criteria of uniformity there may be brightness, texture, color and other parameters. In this work we made texture segmentation of one-channel (one polarization) TerraSAR-X images by use of the proper Haralick second order statistics: ‘contrast’, ‘inverse moment’, ‘sum of squares’, ‘correlation’ and ‘entropy’. With the aim to understand which textural features give the greatest differentiation of objects on the radar image, the Jeffries - Matusita separability for each pair of the classes in amplitude and textural images was calculated and analyzed before and after speckle filtering. The separability measure did not reveal statistics with the better separability between classes, but demonstrated better object differentiation in textural images compared with amplitude images. The images received by textural RGB segmentation, PCA and clustering were compared and analyzed.
Keywords: one channel image, texture features, segmentation, Jeffries - Matusita separability
Full text


  1. Bakut P.A., Kolmogorov G.S., Vornovitskii I.E. Segmentatsiya izobrazhenii: metody porogovoi obrabotki (Image segmentation: methods of threshold processing), Zarubezhnaya radioelektronika, 1987, No.10, pp. 6–24.
  2. Bakut P.A., Kolmogorov G.S., Segmentatsiya izobrazhenii: metody vydeleniya granits oblastei (Image segmentation: methods of area border allocation), Zarubezhnaya radioelektronika, 1987, No. 10, pp. 25–47.
  3. Chochia P.A., Piramidal'nyi algoritm segmentatsii izobrazhenii (Pyramidal algorithm of image segmentation), Informatsionnye protsess, 2010, Vol. 10, No. 1, pp. 23–35.
  4. Haralick R.M., Shanmugam K., Dinstein I., Textural Features for Image Classification, IEEE Trans. Syst. Man and Cybernetics, 1973, Vol. 3, No. 6, pp. 610–621.
  5. Lee J.-S., A Simple Speckle Smoothing Algorithm for Synthetic Aperture Radar Images, IEEE Trans. SMC, 1983, Vol. 13, No.1, pp. 85–89.
  6. Nussbaum S., Menz G. (Eds.), Object-Based Image Analysis and Treaty Verification: New Approaches in Remote Sensing – Applied to Nuclear Facilities in Iran, 2008, Springer Science+Business Media B.V., Dordrecht.
  7. Ulaby F.T., Kouyate F., Brisco B., Williams T.H.L., Textural Information in SAR Images, IEEE Trans. GRS, 1986, Vol. GE-24, No.2, pp. 235–245.