IJMLC 2012 Vol.2(1): 62-71 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2012.V2.90

Speckle Reduction Approach for SAR Image in Satellite Communication

Ashkan Masoomi, Roozbeh Hamzehyan, and Najmeh Cheraghi Shirazi

Abstract—This paper represents a novel approach to improve de-speckling in SAR images. At firstl, Smoothing of the coefficients of the highest wavelet sub-bands is applied on decomposed wavelet coefficients. A Gaussian low pass filter using a tours algorithm has been used to decompose the image. Then, the learning of a Kohonen self organizing map (SOM) is performed directly on the de-noised image to take out the blur. Traditional speckle reduction approaches cause artificial structures, blurred and smoothed image, although intelligent de-blurring technique captured these problems. Quantitative and qualitative comparisons of the results obtained by the new method with the results achieved from the other speckle noise reduction techniques demonstrate its higher performance for speckle reduction in SAR images.

Index Terms—Directional smoothing, de-blurring, de-noising, wavelets.

Ashkan Masoomi is with the Communication Engineering Department of Islamic Azad University, Ahram Branch, Iran. (e-mail: ashkan.masoomi@ yahoo.com).
Roozbeh Hamzehyan is with the Communication Engineering Department of Islamic Azad University, Boushehr Branch, Iran. (e-mail: r_hamzehyan@yahoo.com).
Najmeh Cheraghi Shirazi is with the Electrical Engineering Department of Islamic Azad University, Boushehr Branch, Iran. (e-mail: nch_shirazi@yahoo.com).

[PDF]

Cite: Ashkan Masoomi, Roozbeh Hamzehyan, and Najmeh Cheraghi Shirazi, "Speckle Reduction Approach for SAR Image in Satellite Communication," International Journal of Machine Learning and Computing vol. 2, no. 1, pp. 62-71, 2012.

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Scopus (since 2017), Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net