Nouveau modèle de texture markovien basé sur la loi K : Application à l'echographie

We propose in this article a new model of the coherent imagery texture based on Markov Random field. This model permits to take in account the spatial information of the texture while preserving a local distribution . In order to respect the luminous intensity properties, one chooses to stand locally in the setting of the product model. Thus, the construction of this model implies the construction a Markov random field with a local distribution gamma. This last model is chosen outside of the class of auto-models of Besag in order to be able to control easily its local average. In order to understand the role of the field parameters, a synthetic texture whole is presented here. This model is tested then on textures extracted of echographic pictures.

[1]  K. Schätzel,et al.  K-distributed phase differences in turbulent random phase screens , 1983 .

[2]  B. Goldberg,et al.  Comparisons of the Rayleigh and K-distribution models using in vivo breast and liver tissue. , 1998, Ultrasound in medicine & biology.

[3]  P. Shankar A general statistical model for ultrasonic backscattering from tissues , 2000 .

[4]  J. Goodman Some fundamental properties of speckle , 1976 .

[5]  M.R. Boussema,et al.  Heterogeneous SAR texture characterization by means of Markov random fields , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[6]  P M Shankar,et al.  Use of the K-distribution for classification of breast masses. , 2000, Ultrasound in medicine & biology.

[7]  J. Kong,et al.  K-Distribution and Polarimetric Terrain Radar Clutter , 1990, Progress In Electromagnetics Research.

[8]  E. Jakeman,et al.  Generalized K distribution: a statistical model for weak scattering , 1987 .