Abstract
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.
Similar content being viewed by others
References
Castleman, K. R., Digital Image Processing, Beijing: Tsinghua University Press, Prentice Hall, Inc., 1998.
Pitas, I., Venetsanopoulos, A. N., Nonlinear Digital Filters—Principles and Applications, Boston: Kluwer Academic Publishers, 1990.
Hardie, R. C., Barner, K. E., Rank conditional rank selection filters for signal restoration, IEEE Trans. on Image Processing, 1994, 3: 192–206.
Jeong, B., Lee, Y. H., Design of weighted order statistic filters using the perceptron algorithm, IEEE Trans. on Signal Process, 1994, 42: 3264–3268.
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.
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.
Yin, L., Astola, J., Neuvo, Y., A new class of nonlinear filters—neural filters, IEEE Trans.on Signal Processing, 1993, 41: 1201–1222.
Civanlar, M. R., Trussell, H. J., Digital image restoration using fuzzy sets, IEEE Trans. on Acoust. Speech, Signal Processing, 1986, 34: 919–936.
Arakawa, K., Median filter based on fuzzy rules and its application to image processing, Fuzzy Sets and Systems, 1996, 77: 3–13.
Chen, R. C., Yu, P. T., Fuzzy selection filters for image restoration with neural learning, IEEE Trans. on Signal Processing, 1999, 47: 1446–1450.
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.
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.
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.
Lee, C. S., Kuo, Y. H., Yu, P. T., Weighted fuzzy mean filters for image processing, Fuzzy Sets and Systems, 1997, 89: 157–180.
Liu Puyin, Representation of digital image by fuzzy neural networks, Fuzzy Sets and Systems, 2002(in press).
Russo, F., Ramponi, G., A fuzzy filter for images corrupted by impulse noise, IEEE Signal Process Lett., 1996, 3: 168–170.
Yang, X., Toh, P. S., Adaptive fuzzy multilevel median filter, IEEE Trans on Image Processing, 1995, 4: 680–682.
Liu Puyin, Li Hongxing, Approximation of generalized fuzzy system to integrable function, Science in China, Series E, 2000, 43(5): 618–628.
Liu Puyin, Li Hongxing, Analyses forL p(μ)-norm approximation capability of generalized Mamdani fuzzy systems, Information Science, 2001, 138: 195–210.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, P., Li, H. Image restoration techniques based on fuzzy neural networks. Sci China Ser F 45, 273–285 (2002). https://doi.org/10.1360/02yf9024
Received:
Issue Date:
DOI: https://doi.org/10.1360/02yf9024