Multimedia Tools and Applications

, Volume 78, Issue 2, pp 1785–1804 | Cite as

Fuzzy SVM based fuzzy adaptive filter for denoising impulse noise from color images

  • Amarjit RoyEmail author
  • Rabul Hussain Laskar


Impulse noise is an “On-Off” noise that corrupts an image drastically. Classification of noisy and non-noisy pixels should be performed more accurately so as to restore the corrupted image with less blurring effect and more image details. In this paper, fuzzy c-means (FCM) clustering has been incorporated with fuzzy- support vector machine (FSVM) classifier for classification of noisy and non-noisy pixels in removal of impulse noise from color images. Here, feature vector comprises of newly introduced local binary pattern (LBP) with previously used feature vector prediction error, median value, absolute difference between median and pixel under operation. In this work, features have been extracted from the image corrupted with 10%, 50 and 90% impulse noise respectively and FCM clustering has been used for reduction of size of the feature vector set before processing through FSVM during training procedure. If the pixel is depicted as noisy in testing phase, fuzzy decision based adaptive vector median filtering is performed in accordance with available non-corrupted pixels within the processing window centring the noisy pixel under operation. It has been observed that proposed FSVM based fuzzy adaptive filter provides better performance than some of the established state-of-art filters in terms of PSNR, MSE, SSIM and FSIMC. It is seen that performance is increased by ~4 dB than baseline filters such as modified histogram fuzzy color filter (MHFC) and multiclass SVM based adaptive filter (MSVMAF).


Impulse noise Fuzzy c-means (FCM) clustering Fuzzy-SVM (FSVM) Local binary pattern (LBP) Adaptive filter FSIMC 



The authors would like to acknowledge the Image and Speech Processing Laboratory, Department of Electronics and Communication Engineering, National Institute of Technology Silchar, India for providing support and necessary facilities for carrying out this work. I also want to thank Mr. Mohiul Islam, Ph. D. research scholar of Department of Electronics and Communication Engineering, National Institute of Technology Silchar, India for providing valuable suggestions during preparation of the revised manuscript.


  1. 1.
    Ahmed F, Das S (2014) Removal of high-density salt-and-pepper noise in images with an iterative adaptive fuzzy filter using alpha-trimmed mean. IEEE Trans Fuzzy Syst 22(5):1352–1358CrossRefGoogle Scholar
  2. 2.
    Ahonen T, Hadid A, Pietikäinen M (2004) Face recognition with local binary patterns. In: European Conference on Computer Vision. Springer Berlin Heidelberg, pp. 469–481Google Scholar
  3. 3.
    Astola J, Haavisto P, Neuvo Y (1990) Vector median filters. Proc IEEE 78:678–689CrossRefGoogle Scholar
  4. 4.
    Bhadouria VS, Ghoshal D, Siddiqi AH (2014) A new approach for high density saturated impulse noise removal using decision-based coupled window median filter. SIViP 8(1):71–84CrossRefGoogle Scholar
  5. 5.
    Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167CrossRefGoogle Scholar
  6. 6.
    Chan RH, Chung HW (2005) M Nikolova, Salt-and-Pepper noise removal by median-type noise detectors and detail-preserving regularization. IEEE Transaction on Image Processing 14(10):1479–1485CrossRefGoogle Scholar
  7. 7.
    Chan RH, Hu C, Nikolova M (2004) An iterative procedure for removing random-valued impulse noise. IEEE Signal Processing Letters 11(12):921–924CrossRefGoogle Scholar
  8. 8.
    Chang HW, Zhang QW, Wu QG, Gan Y (2015) Perceptual image quality assessment by independent feature detector. Neurocomputing 151:1142–1152CrossRefGoogle Scholar
  9. 9.
    Esakkirajan S, Veerakumar T, Subramanyam AN, PremChand CH (2011) Removal of high density salt and pepper noise through modified decision based unsymmetric trimmed median filter. IEEE Signal processing letters 18(5):287–290CrossRefGoogle Scholar
  10. 10.
    Ghosh S, Dubey SK (2013) Comparative analysis of k-means and fuzzy c-means algorithms. Int J Adv Comput Sci Appl 4(4):36–39Google Scholar
  11. 11.
    Gonzalez RC, Woods RE (2002) Digital image processing, 2nd ed. Prentice Hall, Upper Saddle River, New JerseyGoogle Scholar
  12. 12.
    Gupta V, Chaurasia V, Shandilya M (2015) Random-valued impulse noise removal using adaptive dual threshold median filter. J Vis Commun Image Represent 26:296–304CrossRefGoogle Scholar
  13. 13.
    Horng SJ, Hsu LY, Li T, Qiao S, Gong X, Chou HH, Khan MK (2013) Using sorted switching median filter to remove high-density impulse noises. J Vis Commun Image Represent 24(7):956–967CrossRefGoogle Scholar
  14. 14.
    Hosseini H, Hessar F (2014) Real-Time Impulse Noise Suppression from Images Using an Efficient Weighted-Average Filtering. IEEE Signal Processing Letters 22(8):1050–1054CrossRefGoogle Scholar
  15. 15.
    Huynh-Thu Q, Garcia MN, Speranza F, Corriveau P, Raake A (2011) Study of rating scales for subjective quality assessment of high-definition video. IEEE Trans Broadcast 57(1):1–14CrossRefGoogle Scholar
  16. 16.
    Jin L, Li D (2007) A switching vector median filter based on the CIELAB color space for color image restoration. Signal Process 87(6):1345–1354CrossRefGoogle Scholar
  17. 17.
    Kaliraj G, Baskar S (2010) An efficient approach for the removal of impulse noise from the corrupted images using neural network based impulse detector. Image Vis Comput 28:458–466CrossRefGoogle Scholar
  18. 18.
    Ko SJ, Lee YH (1991) Center weighted median filters and their applications to image enhancement. IEEE transactions on circuits and systems 38:984–993CrossRefGoogle Scholar
  19. 19.
    Li Y, Sun J, Luo H (2014) A neuro-fuzzy network based impulse noise filtering for gray scale images. Neurocomputing 127:190–199CrossRefGoogle Scholar
  20. 20.
    Lin CF, Wang SD (2002) Fuzzy support vector machines. IEEE Trans Neural Netw 13(2):464–471CrossRefGoogle Scholar
  21. 21.
    Masood S, Hussain A, Jaffar MA, Choi TS (2014) Color differences based fuzzy filter for extremely corrupted color images. Appl Soft Comput 21:107–118CrossRefGoogle Scholar
  22. 22.
    Meher SK, Singhawat B (2014) An improved recursive and adaptive median filter for high density impulse noise. International Journal of Electronics and Communications (AEÜ) 68:1173–1179CrossRefGoogle Scholar
  23. 23.
    Nair MS, Mol PA (2013) Direction based adaptive weighted switching median filter for removing high density impulse noise. Comput Electr Eng 39(2):663–689CrossRefGoogle Scholar
  24. 24.
    Pitas I, Venetsanopoulos AN (1992) Order statistics in digital image processing. Proc IEEE 80:1893–1921CrossRefGoogle Scholar
  25. 25.
    Ramadan ZM (2012) Efficient restoration method for images corrupted with impulse noise, Circuits. Systems, and Signal Processing 31(4):1397–1406MathSciNetCrossRefGoogle Scholar
  26. 26.
    Roy A, Laskar RH (2015) Impulse noise removal based on SVM classification. TENCON-IEEE Region 10 Conference, Macao, p 1–5Google Scholar
  27. 27.
    Roy A, Laskar RH (2015) Multiclass SVM based adaptive filter for removal of high density impulse noise from color images. Appl Soft Comput 48:816–826Google Scholar
  28. 28.
    Roy A, Singha J, Devi SS, Laskar RH (2016) Impulse noise removal using SVM classification based fuzzy filter from gray scale images. Signal Process 128:262–273CrossRefGoogle Scholar
  29. 29.
    Roy A, Manam L, Laskar RH (2018) Region Adaptive Fuzzy Filter: An Approach for Removal of Random-Valued Impulse Noise. IEEE Trans Ind Electron 65:7268–7278CrossRefGoogle Scholar
  30. 30.
    Schulte S, De Witte V, Nachtegael M, Van der Weken D, Kerre EE (2007) Histogram-based fuzzy colour filter for image restoration. Image Vis Comput 25(9):1377–1390CrossRefGoogle Scholar
  31. 31.
    Shen J, Deng RH, Cheng Z, Nie L, Yan S (2015) On robust image spam filtering via comprehensive visual modelling. Pattern Recogn 48:3227–3238CrossRefGoogle Scholar
  32. 32.
    Singh KM, Bora PK (2014) Switching vector median filters based on non-causal linear prediction for detection of impulse noise. Imaging Sci J 62(6):313–326CrossRefGoogle Scholar
  33. 33.
    Sun T, Neuvo Y (1994) Detail-preserving median based filters in image processing. Pattern Recogn Lett 15:341–347CrossRefGoogle Scholar
  34. 34.
    Tukey JW (1974) Nonlinear (nonsuperposable) methods for smoothing data. Proceedings of Congress Record EASCON, Washington DC, p 673Google Scholar
  35. 35.
    Tukey JW (1977) Exploratory data analysis. Addison-Wesley, ReadingGoogle Scholar
  36. 36.
    Wang Z, Bovik AC, Sheikh HR (2004) E P Simoncell, Image quality assessment: From Error Visibility to Structural Similarity. IEEE Transaction on Image Processing 13(4):600–612CrossRefGoogle Scholar
  37. 37.
    Wang X, Shen S, Shi G, Xu Y, Zhang P (2016) Iterative non-local means filter for salt and pepper noise removal. J Vis Commun Image Represent 38:440–450CrossRefGoogle Scholar
  38. 38.
    Wang SH, Sun J, Phillips P, Zhao G, Zhang YD (2017) Polarimetric synthetic aperture radar image segmentation by convolutional neural network using graphical processing units. J Real-Time Image Proc:1–12.
  39. 39.
    Zhang Y, Lenan W (2008) Improved image filter based on SPCNN. Science in China Series F: Information Sciences 51:2115–2125Google Scholar
  40. 40.
    Zhang L, Zhang L, Mou X, Zhang D (2011) FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process 20(8):2378–2386MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringBML Munjal UniversityGurgaonIndia
  2. 2.Department of Electronics and Communication EngineeringNIT, SilcharSilcharIndia

Personalised recommendations