Image restoration techniques based on fuzzy neural networks



By establishing some suitable partitions of input and output spaces, a novel fuzzy neural network (FNN) which is called selection type FNN is developed. Such a system is a multilayer feedforward neural network, which can be a universal approximator with maximum norm. Based on a family of fuzzy inference rules that are of real senses, a simple and useful inference type FNN is constructed. As a result, the fusion of selection type FNN and inference type FNN results in a novel filter—FNN filter. It is simple in structure. And also it is convenient to design the learning algorithm for structural parameters. Further, FNN filter can efficiently suppress impulse noise superimposed on image and preserve fine image structure, simultaneously. Some examples are simulated to confirm the advantages of FNN filter over other filters, such as median filter and adaptive weighted fuzzy mean (AWFM) filter and so on, in suppression of noises and preservation of image structure.


fuzzy neural network selection type FNN inference type FNN FNN filter 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Castleman, K. R., Digital Image Processing, Beijing: Tsinghua University Press, Prentice Hall, Inc., 1998.Google Scholar
  2. 2.
    Pitas, I., Venetsanopoulos, A. N., Nonlinear Digital Filters—Principles and Applications, Boston: Kluwer Academic Publishers, 1990.MATHGoogle Scholar
  3. 3.
    Hardie, R. C., Barner, K. E., Rank conditional rank selection filters for signal restoration, IEEE Trans. on Image Processing, 1994, 3: 192–206.CrossRefGoogle Scholar
  4. 4.
    Jeong, B., Lee, Y. H., Design of weighted order statistic filters using the perceptron algorithm, IEEE Trans. on Signal Process, 1994, 42: 3264–3268.CrossRefGoogle Scholar
  5. 5.
    Ko, S. J., Lee, Y. H., Center weighted median filters and their applications to image enhancement, IEEE Trans. on Circuits and Systems, 1991, 38: 984–993.CrossRefGoogle Scholar
  6. 6.
    Kundu, A., Mitra, S. K., Vaidyanathan, P. P., Application of two-dimensional generalized mean filtering for removal of impulse noises from images, IEEE Trans. on Acoust. Speech, Signal Processing, 1984, 32: 600–609.CrossRefGoogle Scholar
  7. 7.
    Yin, L., Astola, J., Neuvo, Y., A new class of nonlinear filters—neural filters, IEEE Trans.on Signal Processing, 1993, 41: 1201–1222.MATHCrossRefGoogle Scholar
  8. 8.
    Civanlar, M. R., Trussell, H. J., Digital image restoration using fuzzy sets, IEEE Trans. on Acoust. Speech, Signal Processing, 1986, 34: 919–936.CrossRefGoogle Scholar
  9. 9.
    Arakawa, K., Median filter based on fuzzy rules and its application to image processing, Fuzzy Sets and Systems, 1996, 77: 3–13.CrossRefGoogle Scholar
  10. 10.
    Chen, R. C., Yu, P. T., Fuzzy selection filters for image restoration with neural learning, IEEE Trans. on Signal Processing, 1999, 47: 1446–1450.CrossRefGoogle Scholar
  11. 11.
    Chen, R. C., Yu, P. T., Fuzzy stack filters—their definition, fundamental properties and application in image processing, IEEE Trans on Image Processing, 1996, 5: 838–854.CrossRefMathSciNetGoogle Scholar
  12. 12.
    Farbiz, F., Menhaj, M. B., Motamedi, S. A. et al., A new fuzzy logic filter for image enhancement, IEEE Trans. on Systems Man. Cybernet-Part B, 2000, 30: 110–119.CrossRefGoogle Scholar
  13. 13.
    Kuo, Y. H., Lee, C. S., Chen, C. L., High-stability AWFM filter for signal restoration and its hardware design, Fuzzy Sets and Systems, 2000, 114: 185–202.MATHCrossRefGoogle Scholar
  14. 14.
    Lee, C. S., Kuo, Y. H., Yu, P. T., Weighted fuzzy mean filters for image processing, Fuzzy Sets and Systems, 1997, 89: 157–180.CrossRefGoogle Scholar
  15. 15.
    Liu Puyin, Representation of digital image by fuzzy neural networks, Fuzzy Sets and Systems, 2002(in press).Google Scholar
  16. 16.
    Russo, F., Ramponi, G., A fuzzy filter for images corrupted by impulse noise, IEEE Signal Process Lett., 1996, 3: 168–170.CrossRefGoogle Scholar
  17. 17.
    Yang, X., Toh, P. S., Adaptive fuzzy multilevel median filter, IEEE Trans on Image Processing, 1995, 4: 680–682.CrossRefGoogle Scholar
  18. 18.
    Liu Puyin, Li Hongxing, Approximation of generalized fuzzy system to integrable function, Science in China, Series E, 2000, 43(5): 618–628.Google Scholar
  19. 19.
    Liu Puyin, Li Hongxing, Analyses forL p(μ)-norm approximation capability of generalized Mamdani fuzzy systems, Information Science, 2001, 138: 195–210.MATHCrossRefGoogle Scholar

Copyright information

© Science in China Press 2002

Authors and Affiliations

  1. 1.Department of MathematicsBeijing Normal UniversityBeijingChina

Personalised recommendations