Effective Speckle Noise Removal of SAR Image Based on Combination of Modified PCA and HMF with Enhancement

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2018 by IJETT Journal
Volume-61 Number-3
Year of Publication : 2018
Authors : Leelavathi H P and Dr. J Prakash
DOI :  10.14445/22315381/IJETT-V61P228

Citation 

MLA Style: Leelavathi H P and Dr. J Prakash "Effective Speckle Noise Removal of SAR Image Based on Combination of Modified PCA and HMF with Enhancement" International Journal of Engineering Trends and Technology 61.3 (2018): 171-177.

APA Style:Leelavathi H P and Dr. J Prakash (2018). Effective Speckle Noise Removal of SAR Image Based on Combination of Modified PCA and HMF with Enhancement. International Journal of Engineering Trends and Technology, 61(3), 171-177.

Abstract
Despeckle of Sythetic Aperture Radar (SAR) image is a challenging task for the reseachers due to the presence of multiplicative speckle noise caused by scattered radar waves. This multiplicative speckle noise creates echoes that are directly degrades image quality, aslo makes the object identification difficult. From past few decades the number of speckles noise reduction techniques have been developed to restore the perception quality of SAR images, so that the resulting images are well suitable for further undertaking. However, the existing techniques are not able to perserve edge details of the image while reducing speckle noise. The system model proposed in this paper consists of three stages to reduce the speckle noise in the SAR image. The first stage of the proposed model consists of two stage block based modified Principal Componet Analysis (PCA) which removes maximum amount of speckle noise in SAR image. This block based modified PCA is obtain by selecting different values of standard deviation by applying certain technique that can reduce the maximum amount of speckle noise present in the SAR image. The second stage of proposed model consists of Hybrid Median Filter (HMF) that is used to further removal of the multiplicative noise remaining in the modified PCA output image, particulaly to remove the speckle noise at the edges. Final stage is used to enhance the features of the despeckle image using sharpening filter. In order to maintain good image perception quality, in this paper the selection of the standard deviation is an important factor in the proposed system model to effictively reduce the speckle noise with the existing methods. Thus the system method used in this paper produced better experimetal results than existing methods with regarding to both removal of speckle noise with enhancement of image features.

Reference
[1] Hyunho Choi, Jechang Jeong, ”Despeckling images using a preprocessing filter and DWT-based noise reduction techniques”, IEEE Sensors Journal, Vol.18, No.8, pp.3131-3140. April 15, 2018.
[2] Younggi Byun, Jaewan Choi, Youkyung Han, ” An Area-based image fusion scheme for the integration of SAR and Optical Satellite Imagery”, IEEE Journal of selected topics in applied earth observations and remote sensing, Vol.6, No.5, pp. 2212-2221, October 2013.
[3] Norashikin Yahya, ” Subspace-Based Technique For Speckle Noise Reduction In Sar Images ”, Ieee Transactions On Geoscience And Remote Sensing, Vol.52, No.10, pp.6257- 6271 October 2014.
[4] Yao Zhao, Jian Guo Liu, ” Adaptive Total Variation Regularization Based SAR Image Despeckling and Despeckling Evaluation Index ”, IEEE Transactions On Geoscience And Remote Sensing, Vol.53, May 2015.
[5] Fan Yang, Ze Yu, Chunsheng L, ” An Adaptive SAR Image Speckle Reduction Algorithm Based On Undecimated Wavelet Transform and Non-Local Means”, IGARSS, 978-1-5090-3332-4 EEE 2016.
[6] I. Shanthi, ” Speckle Noise Suppression of SAR Color Image using Hybrid Mean Median Filter ”, International Journal of Computer Applications (0975 ? 8887) Volume 31 No.9, October 2011
[7] Zelong Wang , Xintong Tan, Qi Yu, Jubo Zhu,” Sparse PDE for SAR image speckle suppression ” Jouranals of IET Image Process., Vol.11 pp. 425-432, 2017.
[8] Xin Wang, Linlin Ge, Xiaojing, Li, ”Evaluation of Filters For Envisat asar Speckle Suppression in Pasture Area”, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume I-7, 2012 XXII ISPRS Congress, 25 August - 01 September 2012, Melbourne, Australia.
[9] Gerardo Di Martino, ” Scattering-Based Nonlocal Means Sar Despeckling ”, Ieee Transactions On Geoscience And Remote Sensing, Vol. 54, No. 6, June 2016.
[10] M. Afonso n, J. Miguel Sanches, ”Image reconstruction under multiplicative speckle noise using total variation ”, Neurocomputing journal homepage: www.elsevier.com/locate/neucom
[11] Shuyaun Yang, Yueyaun Zhang, Yue Han, ” Speckle reduction of SAR image through dictionary learning and point target enhancing approaches ”, IEEE CIE International Conference, vol.2, pp.1926-1929, Oct. 2011.
[12] Data sets are Available: https://mdacorporation.com/geospatial/ international/satellites/RADARSAT-2/sample-data

Keywords
Sythetic Aperture Radar image, Speckle noise, Despeckle image, Principal Component Analysis, Hybrid median filter.