Geodesic
On the optimality of a new class of 2D recursive filters
Kybernetika, Tome 35 (1999) no. 6, pp. 777-792 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

The purpose of this paper is to prove the minimum variance property of a new class of 2D, recursive, finite-dimensional filters. The filtering algorithms are derived from general basic assumptions underlying the stochastic modelling of an image as a 2D gaussian random field. An appealing feature of the proposed algorithms is that the image pixels are estimated one at a time; this makes it possible to save computation time and memory requirement with respect to the filtering procedures based on strip processing. Experimental results show the effectiveness of the new filtering schemes.
The purpose of this paper is to prove the minimum variance property of a new class of 2D, recursive, finite-dimensional filters. The filtering algorithms are derived from general basic assumptions underlying the stochastic modelling of an image as a 2D gaussian random field. An appealing feature of the proposed algorithms is that the image pixels are estimated one at a time; this makes it possible to save computation time and memory requirement with respect to the filtering procedures based on strip processing. Experimental results show the effectiveness of the new filtering schemes.
Classification : 93C30, 93E11, 94A08
Keywords: minimum variance property; finite-dimensional filter; Gaussian random field; 2D recursive filters; strip processing; image pixels 
@article{KYB_1999_35_6_a9,
     author = {Jetto, Leopoldo},
     title = {On the optimality of a new class of {2D} recursive filters},
     journal = {Kybernetika},
     pages = {777--792},
     year = {1999},
     volume = {35},
     number = {6},
     mrnumber = {1747976},
     zbl = {1274.93261},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_1999_35_6_a9/}
}
TY  - JOUR
AU  - Jetto, Leopoldo
TI  - On the optimality of a new class of 2D recursive filters
JO  - Kybernetika
PY  - 1999
SP  - 777
EP  - 792
VL  - 35
IS  - 6
UR  - http://geodesic.mathdoc.fr/item/KYB_1999_35_6_a9/
LA  - en
ID  - KYB_1999_35_6_a9
ER  - 
%0 Journal Article
%A Jetto, Leopoldo
%T On the optimality of a new class of 2D recursive filters
%J Kybernetika
%D 1999
%P 777-792
%V 35
%N 6
%U http://geodesic.mathdoc.fr/item/KYB_1999_35_6_a9/
%G en
%F KYB_1999_35_6_a9
Jetto, Leopoldo. On the optimality of a new class of 2D recursive filters. Kybernetika, Tome 35 (1999) no. 6, pp. 777-792. http://geodesic.mathdoc.fr/item/KYB_1999_35_6_a9/

[1] Attasi S.: Modeling and recursive estimation for double indexed sequences. In: System Identification: Advances and Case Studies (R. K. Mehra and D. G. Lainiotis, eds.), Academic Press, New York 1976 | MR

[2] Azimi–Sadjadi M. A., Bannour S.: Two–dimensional recursive parameter identification for adaptive Kalman filtering. IEEE Trans. Circuits and Systems CAS–38 (1991), 1077–1081 | DOI

[3] Azimi–Sadjadi M. R., Khorasani K.: Reduced order strip Kalman filtering using singular perturbation method. IEEE Trans. Circuits and Systems CAS–37 (1990),284–290 | MR

[4] Barry P. E., Gran R., Waters C. R.: Two–dimensional filtering – a state space approach. In: Proc. of Conference Decision and Control 1976, pp. 613–618

[5] Bedini M. A., Jetto L.: Realization and performance evaluation of a class of image models for recursive restoration problems. Internat. J. Systems Sci. 22 (1991), 2499–2519 | DOI | Zbl

[6] Biemond J., Gerbrands J. J.: Comparison of some two–dimensional recursive point–to–point estimators based on a DPCM image model. IEEE Trans. Systems Man Cybernet. SMC–10 (1980), 929–936

[7] Santis A. De, Germani A., Jetto L.: Space-variant recursive restoration of noisy images. IEEE Trans. Circuits and Systems CAS–41 (1994), 249–261

[8] Germani A., Jetto L.: Image modeling and restoration: a new approach. Circuits Syst. Sign. Process. 7 (1988), 427–457 | MR | Zbl

[9] Habibi A.: Two–dimensional bayesian estimate of images. Proc. IEEE 60 (1972), 878–883

[10] Jain A. K.: Partial differential equations and finite–difference methods in image processing. Part I: Image representation. J. Optim. Theory Appl. 23 (1977), 65–91 | DOI | MR | Zbl

[11] Jain A. K., Angel E.: Image restoration, modeling and reduction of dimensionality. IEEE Trans. Comput. C-23 (1974), 470–476 | DOI

[12] Jain A. K., Jain J. R.: Partial differential equations and finite difference methods in image processing. Part II: Image restoration. IEEE Trans. Automat. Control AC–23 (1978), 817–833 | DOI

[13] Katayama T.: Restoration of noisy images using a two–dimensional linear model. IEEE Trans. Systems Man Cybernet. SMC–9 (1979), 711–717 | DOI | Zbl

[14] Katayama T.: Estimation of images modeled by a two–dimensional separable autoregressive process. IEEE Trans. Automat. Control AC–26 (1980), 1199–1201 | DOI

[15] Katayama T., Kosaka M.: Recursive filtering algorithm for a two–dimensional system. IEEE Trans. Automat. Control AC–24 (1979), 130–132 | DOI | Zbl

[16] Kaufman H., Woods J. W., Dravida S., Tekalp A. M.: Estimation and identification of two–dimensional images. IEEE Trans. Automat. Control AC–28 (1983), 745–756 | DOI | Zbl

[17] Keshavan H. R., Srinath M. D.: Sequential estimation technique for enhancement of noisy images. IEEE Trans. Comput. C–26 (1977), 971–987 | DOI | Zbl

[18] Keshavan H. R., Srinath M. D.: Enhancement of noisy images using an interpolative model in two dimensions. IEEE Trans. Systems Man Cybernet. SMC–8 (1978), 247–259 | DOI | MR

[19] Liebelt P. B.: An Introduction to Optimal Estimation. Addison–Wesley, Reading, MA 1967 | Zbl

[20] Murphy M. S.: Comments on ‘Recursive filtering algorithm for a two–dimensional system’. IEEE Trans. Automat. Control AC–25 (1980), 336–338 | DOI | Zbl

[21] Murphy M. S., Silverman L. M.: Image model representation and line–by–line recursive restoration. IEEE Trans. Automat. Control AC–23 (1978), 809–816 | DOI

[22] Nahi N. E.: Role of recursive estimation in statistical image enhancement. Proc. IEEE 60 (1972), 872–877

[23] Nahi N. E., Assefi T.: Bayesian recursive image estimation. IEEE Trans. Comput. C–21 (1972), 734–738 | Zbl

[24] Nahi N. E., Franco C. A.: Recursive image enhancement-vector processing. IEEE Trans. Comm. Com–21 (1973), 305–311 | DOI

[25] Panda D. P., Kak A. C.: Recursive Filtering of Pictures. Tech. Rep. TR-EE-76, School of Electrical Engineering, Purdue University, Lafayette, Ind., 1976; also in: A. Rosenfield and A. C. Kak: Digital Picture Processing. Chapter 7. Academic Press, New York 1976

[26] Powell S. R., Silverman L. M.: Modelling of two–dimensional covariance function with application to image enhancement. IEEE Trans. Automat. Control AC–19 (1974), 8–13 | DOI | MR

[27] Strintzis M. G.: Comments on ‘Two-dimensional Bayesian estimate of images’. Proc. IEEE 64 (1976), 1255–1257

[28] Suresh B. R., Shenoi B. A.: The state–space realization of a certain class of two–dimensional systems with applications to image restoration. Computer Graphics and Image Processing 11 (1979), 101–110 | DOI

[29] Suresh B. R., Shenoi B. A.: New results in two–dimensional Kalman filtering with applications to image restoration. IEEE Trans. Circuits and Systems CAS–28 (1981), 307–319 | DOI

[30] Wellstead P. E., Pinto J. R. Caldas: Self tuning filters and predictors for two–dimensional systems. Part I: Algorithms. Internat. J. Control 42 (1985), 479–496 | DOI

[31] Wellstead P. E., Pinto J. R. Caldas: Self tuning filters and predictors for two–dimensional systems. Part II: Smoothing applications. Internat. J. Control 42 (1985), 479–496 | DOI

[32] Woods J. W., Radewan C. H.: Kalman filtering in two dimensions. IEEE Trans. Inform. Theory IT–23 (1977), 809–816 | DOI | MR | Zbl

[33] Yum Y. H., Park S. B.: Optimum recursive filtering of noisy two–dimensional data with sequential parameter identification. IEEE Trans. Pattern Anal. Mach. Intell. PAMI–5 (1983), 337–344 | DOI

[34] Zou C. T., Plotkin E. I., Swamy M. N. S.: 2-D fast Kalman algorithms for adaptive estimation of nonhomogeneous gaussian Markov random field model. IEEE Trans. Circuits and Systems 41 (1994), 678–692 | DOI