Levent GÖKREM, Uğur ERKAN

A new method based on pixel density in salt and pepper noise removal

In this paper, we deliver a new method to remove salt and pepper noise, which we refer to as based on pixel density lter (BPDF). The rst step of the method is to determine whether or not a pixel is noisy, and then we decide on an adaptive window size that accepts the noisy pixel as the center. The most repetitive noiseless pixel value within the window is set as the new pixel value. By using 18 test images, we give the results of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), image enhancement factor (IEF), standard median lter (SMF), adaptive median lter (AMF), adaptive fuzzy lter (AFM), progressive switching median ler (PSMF), decision-based algorithm (DBA), modi ed decision-based unsymmetrical trimmed median lter (MDBUTMF), noise adaptive fuzzy switching median lter (NAFSM), and BPDF. The results show that BPDF produces better results than the above-mentioned methods at low and medium noise density.

PDF

___

[1] Zhang X, Ding F, Tang Z, Yu C. SPN removal with image in painting. Int J Electron Commun 2015; 69: 307-313.
[2] Gonzalez-Hidalgo M, Massanet S, Mir A, Ruiz-Aguilera D. A fuzzy lter for high-density SPN removal. Lect Notes Comp Sci 2013; 8109: 70-79.
[3] Xiao L, Li C, Wu Z, Wang T. An enhancement method for X-ray image via fuzzy noise removal and homomorphic ltering. Neurocomputing 2016; 64: 195: 56-64.
[4] Coupe P, Manjon JV, Robles M, Collins DL. Adaptive multiresolution non-local means lter for three-dimensional magnetic resonance image denoising. IET Image Process 2012; 6: 558-568.
[5] Baljozovic D, Kovacevic B, Baljozovic A. Mixed noise removal lter for multi-channel images based on halfspace deepest location. IET Imag Proc 2013; 7: 310-323.
[6] Vijendran AS, Lukose B. Fast and efficient method for image denoising. IJEIT 2013; 3: 200-208.
[7] Sakthidasan K, Sankaran A, Nagappan VN. Noise free image restoration using hybrid lter with adaptive genetic algorithm. Comput Elec Eng 2016; 54: 382-392.
[8] Thanha DNH, Dvoenkoa SD. A method of total variation to remove the mixed Poisson{Gaussian noise. Pattern Recogn 2016; 26: 285-293.
[9] Zhang C, Wang K. A switching median{mean lter for removal of high-density impulse noise from digital images. Optik 2015; 126: 956-961.
[10] Gellert A, Brad R. Context-based prediction ltering of impulse noise images. IET Image Process 2016; 10: 429-437.
[11] Vasanth K, Kumar VJS. Decision-based neighborhood-referred unsymmetrical trimmed variants lter for the re- moval of high-density salt-and-pepper noise in images and videos. Signal Image Video P 2015; 9: 1833-1841.
[12] Chan RH, Ho CW, Nikolova M. Salt-and-pepper noise removal by median-type noise detectors and detail-preserving regularization. IEEE T Image Process 2005; 14: 1479-1485.
[13] Zhao F, Ma RC, Ma JQ. An algorithm for SPN removal based on information entropy. Appl Mech Mater 2012; 220{223: 2273-2279.
[14] Erkan U, Kilicman A. Two new methods for removing salt-and-pepper noise from digital images. ScienceAsia 2016; 42: 28-32.
[15] Roig B, Estruch VD. Localised rank-ordered differences vector lter for suppression of high-density impulse noise in colour images. IET Image Process 2016; 10: 24-33.
[16] Hwang H, Haddad RA. Adaptive median lters: new algorithms and results. IEEE T Image Process 1995; 4: 499-502.
[17] Jin L, Xiong C, Liu H. Improved bilateral lter for suppressing mixed noise in color images. Digit Signal Process 2012; 22: 903-912.
[18] Sreenivasulu P, Chaitanya NK. Removal of SPN for various images using median lters: a comparative study. IUP J Telecommunications 2014; VI.
[19] Sun C, Tang C, Zhu X, Li X, Wang L. An efficient method for salt-and-pepper noise removal based on shearlet transform and noise detection. Int J Electron Commun. 2015; 69: 1823-1832.
[20] Xiao Y, Zeng T, Yu J, Ng MK. Restoration of images corrupted by mixed Gaussian-impulse noise via l1{l0 minimization. Pattern Recogn 2011; 44: 1708-1720.
[21] Astola J, Kuosmanen P. Fundamentals of Nonlinear Digital Filtering. Boca Raton, FL, USA: CRC Press, 1997.
[22] Tsirikolias K. Low level image processing and analysis using radius lters. Digit Signal Process 2016; 50: 72-83.
[23] Yin L, Yang R, Gabbouj M, Neuvo Y. Weighted median lters: a tutorial. IEEE T Circuits Syst 1996; 43: 157-192.
[24] Arce G. A general weighted median lter structure admitting negative weights. IEEE T Signal Proc 1998; 46: 3195-3205.
[25] Arce G, Paredes J. Recursive weighted median lters admitting negative weights and their optimization. IEEE T Signal Proc 2000; 48: 768-779.
[26] Pattnaik A, Agarwal S, Chand S. A new and efficient method for removal of high density SPN through cascade decision-based ltering algorithm. Procedia Technol 2012; 6: 108-117.
[27] Palabas T, Gangal A. Adaptive fuzzy lter combined with median lter for reducing intensive SPN in gray level images. In: IEEE 2012 International Symposium on Innovations in Intelligent Systems and Applications; 2{4 July 2012; Trabzon, Turkey. New York, NY, USA: IEEE. pp. 1-4.
[28] Shrestha S. Image denoising using new adaptive based medan lter. Signal &. Image Processing: An International Journal 2014; 5: 1-13.
[29] Wang Z, Zhang D. Progressive switching median lter for the removal of impulse noise from highly corrupted images. IEEE T Circuit Syst 1999; 46: 78-80.
[30] Srinivasan KS, Ebenezer D. A new fast and efficient decision-based algorithm for removal of high density impulse noises. IEEE Signal Process 2007; 14: 189-192.
[31] Kesharwani A, Agrawal S, Dhariwal MK. An improved decision based asymmetric trimmed median lter for removal of high density SPN. Int J Comput Appl 2013; 84: 37-43.
[32] Esakkirajan S, Veerakumar T, Subramanyam AN, Prem Chand CH. Removal of high density salt and pepper noise through modi ed decision based unsymmetric trimmed median lter. IEEE Signal Process 2011; 18: 287-290.
[33] Vasanth K, Senthilkumar VJ. A decision based unsymmetrical trimmed midpoint algorithm for the removal of high density SPN. J Theor Appl Inf Technol 2012; 42: 245-252.
[34] Toh KKV, Isa NAM. Noise adaptive fuzzy switching median lter for salt-and-pepper noise reduction. IEEE Signal Process 2010; 17: 281-284.
[35] Zhang P, Li F. A new adaptive weighted mean lter for removing salt-and-pepper noise. IEEE Signal Process 2014; 21: 1280-1283.
[36] Zhou W, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE T Image Process 2004; 13: 600-612.