Réduction du nombre de niveaux de lissage dans une structure de filtre LUM FTC

Réduction du nombre de niveaux de lissage dans une structure de filtre LUM FTC

Reduction of smoothing levels in LUM FTC filter structure

Rastislav Lukác Viktor Fischer  Nathalie Bochard 

Slovak Image Processing Center, Jarkova 343, 049 25 Dobsina, Slovakia.

Laboratoire Traitement du Signal et Instrumentation, Unité Mixte de Recherche CNRS 5516, Université Jean Monnet, Saint-Etienne, France

Corresponding Author Email: 
lukacr@ieee.org
Page: 
89-96
|
Received: 
1 July 2000
| |
Accepted: 
N/A
| | Citation

OPEN ACCESS

Abstract: 

In this paper, we analyze the possibility of the reduction of smoothing levels in 3-D adaptive lower-upper-middle (LUM) smoother based on the fixed threshold control (FTC). Besides the excellent noise attenuation capability with the simultaneous signal-detail preservation, recently introduced LUM FTC filter with a window size N is characterized by a relatively complex structure, where an estimate is formed according to (N +1)/2 decision rules. This fact can constrain its possible hardware filter implementation in real motion video applications. In order to simplify the filter complexity, however, to retain the excellent filter performance simultaneously, we propose two approaches such as linear reduction of smoothing levels and optimal reduction based on genetic algorithm.

Résumé

Dans cet article, nous analysons la possibilité de réduire le nombre de niveaux de lissage d’un filtre LUM (lower-upper-middle) adaptatif 3-D basé sur un contrôle par seuils fixes (FTC = fixed threshold control). Outre son excellente capacité d’atténuation du bruit tout en assurant la conservation des détails, le filtre LUM FTC avec une fenêtre de taille N, est caractérisé par une structure relativement complexe, où l’estimation de la valeur de sortie est faite en fonction de (N + 1)/2 règles de décision. Ceci peut entraver l’implémentation matérielle de tels filtres dans des applications vidéo temps réel. Afin de simplifier la complexité du filtre tout en gardant ses excellentes performances, nous proposons deux approches qui sont la réduction linéaire du nombre de niveaux de lissage et la réduction optimale basée sur un algorithme génétique.

Keywords: 

Image sequences, order statistics, LUM smoother, adaptive filter, impulse noise

Mots clés

Séquences d’images, statistiques d’ordre, filtre LUM, filtre adaptatif, bruit impulsionnel

1. Introduction
2. Filtre LUM FTC
3. Réduction De La Complexité Du Filtre
4. Résultats Expérimentaux
5. Conclusion
  References

[1] Arce G.R., Multistage Order Statistic Filters for Image Sequence Processing. IEEE Transaction on Signal Processing, vol.39, No.5, May 1991, pp. 1146-1163.

[2] Astola J. and Kuosmanen P., Fundamentals of Nonlinear Digital Filtering. CRC Press, 1997.

[3] Bolon P., Filtrage d’ordre, vraisemblance et optimalités des prétraitements d’images. Traitement du Signal, Vol. 9, No. 3, 1992, pp. 225-250.

[4] Boncelet C., Image Noise Models. In Handbook of Image and Video Processing (ed. A. Bovik), Academic Press, 2000.

[5] Fischer V., Drutarovsky´ M., Lukac R., Implementation of 3-D Adaptive LUM Smoother in Reconfigurable Hardware. Proceedings of the 12th International Conference on Field Programmable Logic and Applications FPL 2002 in Montpellier (La Grande Motte), France, September 2-4, 2002, in Springer Verlag LNCS 2438, pp.720-729.

[6] Gabbouj M., Coyle E. J. and Gallagher N. C., An Overview of Median and Stack Filtering. Circuit Systems Signal Processing, Vol.11, No.1, 1992, pp. 7-45.

[7] Goldberg D., Genetic Algorithms in Search, Optimisation, and Machine Learning. Addison-Wesley, Reading, Massachutts, 1989.

[8] Hardie R.C. and Boncelet C.G., LUM Filters: A Class of Rank-OrderBased Filters for Smoothing and Sharpening. IEEE Transaction on Signal Processing, Vol. 41, No. 3, pp. 1061-1076, March 1993.

[9] Klima M., Dvorak P., Zahradník P., Kolar J., and Kott P., Motion Detection and Target Tracking in a TV Image for Security Purposes. Proc. 28th International IEEE Carnahan Conference on Security Technology 1994 in Albuquerque USA, pp. 43-44, 1994.

[10] Kotropoulos C. and Pitas I., Adaptive LMS L-Filters for Noise Suppression in Image. IEEE Transactions on Image Processing, Vol.5, No. 12, December 1996, pp. 1596-1609.

[11] Kotropoulos C. and Pitas I., Nonlinear Model-Based Image /Video Processing and Analysis. John Willey and Sons, 2001.

[12] Lagendijk R.L., Roosmalen P.M., Biemond J., Video Enhancement and Restoration. In Handbook of Image and Video Processing (ed. A. Bovik), Academic Press, 2000.

[13] Lukac R. and Marchevsky´ S., LUM Smoother with Smooth Control for Noisy Image Sequences. EURASIP Journal on Applied Signal Processing, Vol. 2001, No. 2, pp. 110-120, June 2001.

[14] Lukac R. and Marchevsky´ S., Boolean Expression of LUM Smoothers. IEEE Signal Processing Letters, Vol. 8, No. 11, pp. 292-294, November 2001.

[15] Lukac R., Fischer V. and Drutarovsky´ M, 3-D Adaptive LUM Smoother Based On Reduced Set of Smoothing Levels. Proceedings of the 9th IEEE International Conference on Electronics, Circuits and Systems in Dubrovnik, Croatia, September 15-18, 2002, Vol.3, pp.871-874.

[16] Lukac R., Binary LUM Smoothing, IEEE Signal Processing Letters, Vol.9, (2002) 400-403.

[17] Man K.F., Tang T.S. and Kwong S., Genetic ALgorithm. SpringerVerlag, London 1999.

[18] Moyne L., Porter L., Passino K. M., Genetic Adaptive Observers. Engineering of Applied Artificial Intelligence. Vol.8, (1995) 261-269

[19] Nikolaidis N. and Pitas I., 3-D Image Processing Algorithms. John Wiley & Sons, 2000.

[20] Ozkan M.K., Sezan M.I., and Tekalp A.M., Adaptive Motion – Compensated Filtering of Noisy Image Sequences, IEEE Transaction on Circuits and Systems for Video Technology, vol.3, No.4, August 1993, pp. 277-290.

[21] Peltonen S., Gabbouj M., and Astola J., Nonlinear Filter Design: Methodologies and Challenges, Proc. 2nd IEEE Region 8-EURASIP Symposium on Image and Signal Processing and Analysis ISPA’01 in Pula, Croatia, 2001, pp.102-106.

[22] Pitas I., and Venetsanopoulos A. N., Order Statistics in Digital Image Processing. Proceedings of the IEEE, Vol. 80, No. 12, December 1992, pp.1892-1919.

[23] Salomon R., Evolutionary Algorithms and Gradient Search: Similarities and Differences. IEEE Transactions on Evolutionary Computations, Vol. 2, No. 2, July 1998 pp.45-55.

[24] Tukey J.W., Exploratory Data Analysis. Reading, MA: AddisonWesley, 1970.

[25] Yin L., Yang R., Gabbouj M. and Neuvo Y., Weighted Median Filters: A Tutorial, IEEE Transactions on Circuits and Systems -II, Vol. 43, No. 3, March 1996 pp. 157-192.

[26] Zahradnik P., Klima M., and Cuda J., Real Time Video Motion Detection based on the TMS 320C50 Signal Processor. Proceedings of The Texas Instruments Educators Conference, pp. 51-53, 1995.