Unsupervised and Supervised Classification of PolSAR Image Using Decomposition Techniques: An Analysis from L-Band SIR-C Data

Mudassar Akhtar Shaikh, Prakash Waghji Khirade, Shafiyoddin Badruddin Sayyad


The classification of Polarimetric Synthetic Aperture Radar (PolSAR) image has become a very important task after availability of data by using different techniques. In this paper L-band Quad Pole SIR-C PolSAR dataset of Kolkata City, India is used. We applied different unsupervised and supervised classification techniques on SIR-C dataset. The unsupervised classification techniques include like H-alpha, Wishart H-alpha and Wishart H-A-alpha, whereas in supervised classification classes can be made manually using clustering process. This paper presents the comparison of unsupervised and supervised classification on the basis of four major classes like water, open land, vegetation and settlement. In unsupervised classification we observed that the Wishart H-A-alpha classified image is not only better than H-alpha and Wishart H-alpha classified image but also better than supervised classification for classification PolSAR image analysis.


SAR, PolSAR, Unsupervised, Supervised Classification.

Full Text:



Cloude S. and Pottier E. (1996). A review of target decomposition theorems in radar polarimetry. IEEE Transactions of Geoscience and Remote Sensing. 34, (2), 498-518.

Cloude S. R. and Pottier E. (1997). An entropy based classification scheme for land applications of polarimetric SAR. IEEE IGRS. 35, (1), 68-78.

Domenico S., Paolo F., Giovanni S., Paolo D. M., Marco C. (1996). Analysis of SIR-C/X-SAR data on montespertoli test site. Department di Informatics, Sistemi e Produzione University Tor Vergata, Roma, Italy.

Dong Y, Forester B, Ticehurst C. (1997). Radar backscatter analysis for urban environment. International Journal of Remote Sensing. 18, (6), 1352-1364.

Jensen R. J. (2014). Remote Sensing of the Environment an Earth Resource Perspective. (2nd ed.) Pearson.

L- Band SIR-C Dataset download from http://earthexplorer.usgs.gov/

Lee J. S., Grunes M. R., Ainsworth T. L., Du L. J., Schuler D. L., Cloude S. R. (1999). Unsupervised classification using polarimetric decomposition and complex wishart distribution. IEEE Transactions Geoscience and Remote Sensing. 37/1, (5), 2249-2259.

Lillesand T. M., Kiefer R.W. (1999). Remote Sensing and Image Interpretation. (4th ed.). John Wiley & Sons, Inc.

Sayyad S. B., Khirade P. W., Shaikh M. A. (2015). Speckle filtering of microwave c-band fine quad polarized RADARSAT-2 SAR image using mean and median filter. Bionano Frontier. 8, (3), 294-297.

Shaikh M. A., Gadkar V. B., Sayyad S. B. (2015). SAR image analysis for microwave c-band fine quad polarised RADARSAT-2 using decomposition and speckle filter technique. International Journal of Innovations in Engineering, Research and Technology (IJIERT), Issue ICITDCEME’15, Novateur Publication’s.

Touzi R., Boerner W.M., Lee J.S., and Lueneburg E. (2004). A review of polarimetry in the context of synthetic aperture radar: concepts and information extraction. Can. Journal. Remote Sensing. 30, (3), 380–407.

Ouarzeddine M., and Souissi B. Unsupervised classification using wishart classifier. USTHB, F.E.I, BP No 32 EI Alia Bab Ezzouar, Alger.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.