Abstract
A decision-based filtering technique is proposed for removing impulsive noise while preserving image details in corrupted images. The proposed filter is based on support vector machines (SVMs), evidence theory, and the least mean square (LMS) learning algorithm. The fusion of evidence based on the Dempster–Shafer evidence theory provides a feature vector that is used as the input data of the proposed SVM impulse detector, which is used to judge whether an input pixel is noisy. If a pixel is detected as noisy, an adaptive CWM filter based on a weight controller is triggered to replace it; otherwise, the pixel stays unchanged. The optimal weights of the adaptive CWM filter are obtained using scalar quantization and the LMS learning algorithm. Experimental results demonstrate that the proposed filter achieves much better performance than the state-of-the-art filters in terms of noise suppression and detail preservation.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig3_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig4_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig5_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig6_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig7_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-011-0648-9/MediaObjects/521_2011_648_Fig8_HTML.gif)
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Astola J, Kuosmanen P (1997) Fundamentals of nonlinear digital filtering. CRC, Boca Raton
Lukac R, Smolka B, Martin K, Plataniotis KN, Venetsanopoulos AN (2005) Vector filtering for color imaging. IEEE Signal Process Mag 22:74–86
Lin T-C, Yu P-T (2004) Adaptive two-pass median filter based on support vector machines for image restoration. Neural Comput 16:333–354
Sa PK, Majhi B (2010) An improved adaptive impulsive noise suppression scheme for digital images. Int J Electron Commun 64:322–328
Arakawa K (1996) Median filters based on fuzzy rules and its application to image restoration. Fuzzy Sets Syst 77:3–13
Camarena J-G, Gregori V, Morillas S, Sapena A (2010) Some improvements for image filtering using peer group techniques. Image Vis Comput 28:188–201
Chen T, Ma KK, Chen LH (1999) Tri-state median filter for image denoising. IEEE Trans Image Process 8:1834–1838
Hussain A, Jaffar MA, Mirza AM, Chaudhry A (2009) Detail preserving fuzzy filter for impulse noise removal. Int J Innov Comput Inf Control 5:3583–3592
Chen T, Wu HR (2001) Application of partition-based median type filters for suppressing noise in images. IEEE Trans Image Process 10:829–836
Lin T-C, Yu P-T (2004) Partition fuzzy median filter based on fuzzy rules for image restoration. Fuzzy Sets Syst 147:75–97
Lin T-C, Yu P-T (2006) Thresholding noise-free ordered mean filter based on Dempster-Shafer theory for image restoration. IEEE Trans Circuits Syst I Regul Pap 53:1057–1064
Lin T-C (2007) A new adaptive center weighted median filter for suppressing noise in images. Inf Sci 177:1073–1087
Lin T-C (2008) Partition belief median filter based on Dempster-Shafer theory in image processing. Pattern Recognit 41:139–151
Schulte S, Witte VD, Nachtegael M, Weken DV, der Kerre EE (2007) Fuzzy random impulse noise reduction method. Fuzzy Sets Syst 158:270–283
Smolka B, Chydzinski A (2005) Fast detection and impulsive noise removal in color images. Real Time Imaging 11:389–402
Sun T, Neuvo Y (1994) Detail-preserving median based filters in image processing. Pattern Recognit Lett 15:341–347
Ko SJ, Lee YH (1991) Center weighted median filters and their applications to image enhancement. IEEE Trans Circuits Syst 38:984–993
Yin L, Yang R, Gabbouj M, Neuvo Y (1996) Weighted median filters: a tutorial. IEEE Trans Circuits Syst 43:157–192
Kotropoulos C, Pitas I (1996) Adaptive LMS L-filters for noise suppression in images. IEEE Trans Image Process 5:1596–1609
Ohno S, Sakai H (2001) Convergence behavior of the LMS algorithm in subband adaptive filtering. Signal Process 81:1053–1059
Sayood K (2000) Introduction to data compression, 2nd edn. Morgan Kaufmann, Burlington
Wang H, Liu J, Augusto JC (2010) Mass function derivation and combination in multivariate data spaces. Inf Sci 180:813–819
Shafer G (1976) A mathematical theory of evidence. Princeton University Press, Princeton
Vapnik V (1995) The nature of statistical learning theory. Springer, New York
Vapnik V (1998) Statistical learning theory. Wiley, New York
Wang H, McClean S (2008) Deriving evidence theoretical functions in multivariate data space. IEEE Trans Syst Man Cybern 38:455–465
Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice-Hall, Englewood Cliffs
Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge
Chang C-C, Lin C-J (2002) Training nu-support vector regression: theory and algorithms. Neural Comput 14:1959–1977
Hsu C-W, Lin C-J (2002) A simple decomposition method for support vector machines. Mach Learn 46:291–314
Lin C-J (2002) A formal analysis of stopping criteria of decomposition methods for support vector machines. IEEE Trans Neural Netw 13:1045–1052
Lin KM, Lin CJ (2003) A study on reduced support vector machines. IEEE Trans Neural Netw 14:1449–1459
Acknowledgments
The authors would like to thank Prof. Chih-Jen Lin for providing LIBSVM software, a library for support vector machines (version 2.83), and the National Science Council of the Republic of China for financially supporting this research under grant NSC 99-2628-E-274-011.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, TC. Decision-based filter based on SVM and evidence theory for image noise removal. Neural Comput & Applic 21, 695–703 (2012). https://doi.org/10.1007/s00521-011-0648-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0648-9