Abstract
This paper extends the Bayesian direct deconvolution method to the case in which the convolution kernel depends on few unknown nuisance parameters. Moreover, an acceleration procedure is proposed that drastically reduces the computational burden. Finally, the implementation of the method by means of the fast Fourier transform is fully discussed in the multidimensional case.
Similar content being viewed by others
References
Barone P, Rossi C (1986) An E-M method for fast deconvolution. In: Proceedings of COMPSTAT 1986, Short Communications and Posters. Roma, Italy, September 1–6, pp 27–28
Bergland GD, Dolan MT (1979) Fast Fourier transform algorithms. In: Programs for digital signal processing. IEEE Press, New York, Chap 1, pp 1.2–1, 1.2–18
Dempster AP, Laird NM, Rubin DH (1977) Maximum likelihood from incomplete data via E-M algorithm. Journal of the Royal Statistical Society Series B 39:1–38
Di Gesù V, Maccarone MC (1984) The Bayesian direct deconvolution method: Properties and applications. Signal Processing 6:201–211
Fabi F, Rossi C (1983) Decomposition of mixtures via a generalized E-M method. Metron 41:133–146
Kennett TJ, Prestwich WV, Robertson A (1978) Bayesian deconvolution: Convergent properties. Nuclear Instruments and Methods 153:285–292
O'Sullivan F (1986) A statistical perspective on ill-posed inverse problems. Statistical Science 1(4):502–527
Redner RA, Walkner HF (1984) Mixture densities, maximum likelihood and the E-M algorithm. SIAM Review 26:195–239
Rosenfeld A, Kak A (1982) Digital picture processing. Academic Press, New York
Rossi C (1987) General software for the analysis of cytofluorimetric data by EM methods. Computer Mathematical Applications 14:771–782
Rossi C (1988) Robustezza del metodo EM per la scomposizione di misture finite. In: Proceedings of the Thirty-fourth Scientific Meeting of the Italian Statistical Society. Vol. 2, pp 35–42
Shapiro HM (1988) Practical flow cytometry. Alan R. Liss, Inc., New York
Stewart GW (1973) Introduction to matrix computations. Academic Press, New York, Chap 6, pp 317–325
Tikhonov A, Arsenin V (1977) Solution of ill-posed problems. John Wiley and Sons, New York
Titterington DM, Rossi C (1985) Another look at a Bayesian direct deconvolution method. Signal Processing 9:101–106
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Barone, F., Rossi, C. Deconvolution with partially known kernel of nonnegative signals. Machine Vis. Apps. 3, 107–115 (1990). https://doi.org/10.1007/BF01212194
Issue Date:
DOI: https://doi.org/10.1007/BF01212194