Jie ZHAO, Shuaiqi LIU, Qi HU, Pengfei LI, Zhihui ZHU

SAR image denoising based on patch ordering in nonsubsample shearlet domain

Synthetic aperture radar (SAR) has been extensively adopted in a variety of fields, e.g., agriculture andmarine fields. In this regard, the improvement of SAR image quality has aroused a wide concern worldwide. In recentyears, image processing based on local patches has been very popular and proven feasible. In this paper, a novelSAR image denoising algorithm is proposed in the NSST domain on the basis of patch ordering. First, the shearlettransform is applied to logarithmic transformation of the noisy SAR image. Second, the coefficients of the shearlet aredenoised respectively by combining patch ordering and 1D filtering. Finally, the denoised SAR image can be obtainedby exponential transformation after applying the inverse shearlet to denoised coefficients. The experimental results showthat the proposed method not only effectively suppresses the speckle noise and improves the PSNR and ENL of denoisingthe SAR images but also obviously improves the visual effects of the SAR images, especially in maintaining the imageedge and texture information.

PDF

___

[1] Wang Y, Ainsworth TL, Lee JS. Application of mixture regression for improved polarimetric SAR speckle filtering. IEEE T Geosci Remote 2016; 55: 453-467.
[2] Lobry S, Denis L, Tupin F. Multitemporal SAR image decomposition into strong scatterers, background, and speckle. IEEE J-Stars 2016; 9: 3419-3429.
[3] Lee JS, Jurkevich L, Dewaele P, Wambacq P, Oosterlinck A. Speckle filtering of synthetic aperture radar images: a review. Remote Sensing Reviews 1994; 8: 255-267.
[4] Frost VS, Stiles JA, Shanmugan KS, Holtzman JC. A model for radar image and its application to adaptive digital filtering of multiplicative noise. IEEE T Pattern Anal 2009; 4: 157-166.
[5] Martino GD, Simone AD, Iodice A, Riccio D. Scattering-based nonlocal means SAR despeckling. IEEE T Geosci Remote 2016; 54: 3574-3588.
[6] Dai M, Peng C, Chan AK, Loguinov D. Bayesian wavelet shrinkage with edge detection for SAR image despeckling. IEEE T Geosci Remote 2004; 42: 1642-1648.
[7] Fang J, Wang D, Xiao Y, Saikrishna DA. De-noising of SAR images based on Wavelet-Contourlet domain and PCA. In: IEEE 2015 International Conference on Signal Processing; 25–26 April 2015; Beijing, China. New York, NY, USA: IEEE. pp. 942-945.
[8] Liu SQ, Liu M, Li P, Zhao J, Zhu ZH, Wang XH. SAR image denoising via sparse representation in Shearlet domain based on continuous cycle spinning. IEEE T Geosci Remote 2017; 55: 2985-2992.
[9] Karami A, Heylen R, Scheunders P. Band-specific shearlet-based hyperspectral image noise reduction. IEEE T Geosci Remote 2015; 53: 5054-5066.
[10] Lim WQ. The discrete shearlets transform: a new directional transform and compactly supported shearlets frames. IEEE T Image Process 2010; 19: 1166-1180.
[11] Sharifymoghaddam M, Beheshti S, Elahi P, Hashemi M. Similarity validation based nonlocal means image denoising. IEEE Signal Proc Let 2015; 22: 2185-2188.
[12] Chatterjee P, Milanfar P. Clustering-based de-noising with locally learned dictionaries. IEEE T Image Process 2009; 18: 1438-1451.
[13] Yu G, Sapiro G, Mallat S. Solving inverse problems with piecewise linear estimators: from Gaussian mixture models to structured sparsity. IEEE T Image Process 2012; 21: 2481-2499.
[14] Zoran D, Weiss Y. From learning models of natural image patches to whole image restoration. In: IEEE 2011 International Conference on Computer Vision; 6–13 November 2011; Barcelona, Spain. New York, NY, USA: IEEE. pp. 479-486.
[15] Elad M, Aharon M. Image de-noising via sparse and redundant representations over learned dictionaries. IEEE T Image Process 2006; 15: 3736-3745.
[16] Rasti B, Ulfarsson MO, Ghamisi P. Automatic hyperspectral image restoration using sparse and low-rank modeling. IEEE Geosci Remote S 2017; 14: 2335-2339.
[17] Dabov K, Foi A, Katkovnik V, Egiazarian K. Image de-noising by sparse 3-D transform-domain collaborative filtering. IEEE T Image Process 2007; 16: 2080-2095.
[18] Ram I, Cohen I, Elad M. Patch-ordering-based wavelet frame and its use in inverse problems. IEEE T Image Process 2014; 23: 2779-2792.
[19] Ram I, Elad M, Cohen I. Redundant wavelets on graphs and high dimensional data clouds. IEEE Signal Proc Let 2012; 19: 291-294.
[20] Xue B, Huang Y, Yang J, Shi L, Zhan Y, Cao X. Fast nonlocal remote sensing image denoising using cosine integral images. IEEE Geosci Remote S 2013; 10: 1309-1313.
[21] Liu SQ, Hu SH, Xiao Y, An YL. Bayesian Shearlet shrinkage for SAR image de-noising via sparse representation. Multidim Syst Sign P 2014; 25: 683-701.
[22] Fabbrini L, Greco M, Messina M, Pinelli G. Improved anisotropic diffusion filtering for SAR image despeckling. Electron Lett 2013; 49: 672-674.
[23] Liu SQ, Geng P, Shi M, Fang J, Hu S. SAR image de-noising based on generalized non-local means in non-subsample Shearlet domain. In: CSPS 2015 International Conference on Communications, Signal Processing, and Systems; 23–24 October 2015; Sichuan, China. Berlin, Germany: CSPS. pp. 221-229.
[24] Liu SQ, Zhang Y, Hu Q, Liu M, Zhao J. SAR image de-noising based on GNL-means with optimized pixel-wise weighting in non-subsample shearlet domain. Stud Comp Intell 2017; 10: 16-22.
[25] Gomez L, Ospina R, Frery AC. Unassisted quantitative evaluation of despeckling filters. Remote Sens-Basel 2017; 9: 389-392.