Abstract
To attenuate white noise, nonstationary noise and impulse noise are important for signal processing. In this letter, we present nonlinear fusion filters (NFF) based on prediction and smoothing. By means of least square fitting of a polynomial, we define and give the operators of left prediction and right prediction, left smoothing and right smoothing, central smoothing and cross-validation smoothing. In simulated experiments, it is shown that the present method is an effective one.
References
Cheng, Q., Zhou, X. B., Climate change by cluster analysis, Acta Geophysica Sinica, 1998, 41(3): 308:
Pitas, I., Venetsanoponlous, A., Order statistics in digital image processing, Pro. IEEE, 1992, 80: 1893.
Heinonen, P., Neuvo, Y., FIR-median hybrid filters with predictive FIR substructures, IEEE Trans. ASSP, 1988, 36: 892.
Flaig, A., Arce, G. R., Barner, K. E., Affine order-statistic filters: “Medianization” of linear FIR filters, IEEE Trans. Signal Processing, 1998, 46(8): 2101.
Donoho, D. L., Johnstone, I. M., Ideal spatial adaption via wavelet shrinkage, Biometrika, 1994, 81: 425.
Eubank, R., Spline Smoothing and Nonparametric Regression, New York: Dekker, 1988.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Cheng, Q., Zhou, X. & Sun, X. Nonlinear fusion filters based on prediction and smoothing. Chin.Sci.Bull. 45, 1726–1728 (2000). https://doi.org/10.1007/BF02898996
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02898996