Abstract
Common fuzzy radial basis function neural network (F-RBFNN) behaves the capability of the approximation of nonlinear noise signal and can denoise images well. In F-RBFNN, the knowledge expression of fuzzy logic and the reasoning ability are combined with the RBFNN’s capabilities of fast learning and generalization. And the F-RBFNN’s structure and parameters can be adjusted according to the real problem. But this model can not overcome the detect of redundant fuzzy rule so that the optimized learning speed is too slow. To avoid this problem, considering the modified structure and learning algorithm of the antecedent and subsequent network of F-RBFNN, an improved F-RBFNN is proposed and used to denoise millimeter wave (MMW) images. At the same time, to obtain high-quality restored image, the method of sparse representation with the self-adaptive denoising property is used again to denoise results obtained by F-RBFNN. Using the relative single noise ratio (RSNR) criterion to measure denoised images, simulation experimental results show that, compared with other denoising methods such as F-RBFNN, RBFNN and K-SVD and so on, this combination denoising method can obtain better restored images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Takagi, T., Sugeno, M.: Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybern. 1, 116–132 (1985)
Sugeno, M., Kang, G.T.: Structure identification of fuzzy model. Fuzzy Sets Syst. (SO165-0114) 28(1), 15–33 (1988)
Liu, J.Z., Hu, Y., Liu, Z.W.: Effective approach for t-s fuzzy modeling and its application. J. Syst. Simul. 25(12), 2828–2832 (2013)
Wei, F.: Study on filtering image impulse noise based on fuzzy neural network method. Laser J. 37(1), 131–134 (2016)
Guillén, A.N., Rojas, I., González, J., Pomares, H., Herrera, LJ., Prieto, A.: A fuzzy-possibilistic fuzzy ruled clustering algorithm for RBFNNs design. In: Greco, S., Hata, Y., Hirano, S., Inuiguchi, M., Miyamoto, S., Nguyen, H.S., Słowiński, R. (eds.) RSCTC 2006. LNCS(LNAI), vol. 4259, pp. 647–656. Springer, Heidelberg (2006). doi:10.1007/11908029_67
Yang, N., Chen, H.J., Li, Y.F.: Coupled parameter optimization of PCNN model and vehicle image segmentation. J. Transp. Syst. Eng. Inf. Technol. 12(1), 48–54 (2012)
Lu, J.Z., Zhang, Q.H., Xu, Z.Y., Peng, Z.M.: Image super-resolution reconstruction algorithm using over-complete sparse representation. Syst. Eng. Electron. 34(2), 403–408 (2012)
Sun, J., Xu, Z.B., Shum, H.Y.: Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Trans. Image Process. 20(6), 1529–1542 (2011)
Luo, J.H., Son L.X., Li L.M., Luo S.X.: Nonlinear filtering based fuzzy RBF neural network. Comput. Simul., 133–136 (2006)
Luo, J.H., Li, L.M., Ye, D.X., Zhou, H.L.: Noise cancellation based on improved RBF fuzzy neural network filtering. J. Syst. Simul. 19(21), 4918–4921 (2007)
Liu, J., Tai, X.C., Huang, H.: A weighted dictionary learning model for denoising images corrupted by mixed noise. IEEE Trans. Image Process. 22(3), 1108–1120 (2013)
Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006)
Yang, J.C., Wright, J., Huang, T., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)
Elad, M., Datsenko, D.: Example-based regularization deployed to super-resolution reconstruction of a single image. Comput. J. 52(1), 15–30 (2008)
Yang, J.C., Wright, J., Huang, T., Ma, Y.: Image super-resolution via sparse representation of raw image patches. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). LNCS, vol. 322, pp. 1–8. Springer, Heidelberg (2008)
Acknowledgement
This work was supported by the grants from National Nature Science Foundation of China (Grant No. 61373098 and 61370109), the youth found of Natural Science Foundation of Jiangsu Province of China (Grant No. BK20160361), and the grant from Natural Science Foundation of Anhui Province (No. 1308085MF85).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Shang, L., Zhou, Y., Sun, Z. (2017). MMW Image Restoration Using the Combination Method of Modified Fuzzy RBFNN and Sparse Representation. In: Huang, DS., Bevilacqua, V., Premaratne, P., Gupta, P. (eds) Intelligent Computing Theories and Application. ICIC 2017. Lecture Notes in Computer Science(), vol 10361. Springer, Cham. https://doi.org/10.1007/978-3-319-63309-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-63309-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63308-4
Online ISBN: 978-3-319-63309-1
eBook Packages: Computer ScienceComputer Science (R0)