Anisotropic analysis of some Gaussian models

被引:119
作者
Bonami, A [1 ]
Estrade, A
机构
[1] Univ Orleans, Dept Math, MAPMO UMR 6628, F-45067 Orleans 2, France
[2] Univ Orleans, Dept Math, MAPMO UMR 6628, F-45067 Orleans 2, France
关键词
fractal analysis; anisotropic Gaussian fields; asymptotic self-similarity;
D O I
10.1007/s00041-003-0012-2
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
Although the classical Fractional Brownian Motion is often used to describe porosity, it is not adapted to anisotropic situations. In the present work, we study a class of Gaussian fields with stationary increments and "spectral density." They present asymptotic self-similarity properties and are good candidates to model a homogeneous anisotropic material, or its radiographic images. Unfortunately, the paths of all Gaussian fields with stationary increments have the same apparent regularity in all directions (except at most one). Hence we propose here a procedure to recover anisotropy from one realization: computing averages over all the hyperplanes which are orthogonal to a fixed direction, we get a process whose Holder regularity depends explicitly on the asymptotic behavior of the spectral density in this direction.
引用
收藏
页码:215 / 236
页数:22
相关论文
共 22 条
[1]  
ADLER AJ, 1981, GEOMETRY RANDOM FIEL
[2]  
Ayache A., 2000, STAT INFERENCE STOCH, V1, P7
[3]  
Benassi A, 1997, REV MAT IBEROAM, V13, P19
[4]  
Cramer H., 1967, Stationary and Related Stochastic Processes. Sample Function. Properties and Their Applications
[5]   Fractal analysis of surface roughness by using spatial data [J].
Davies, S ;
Hall, P .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1999, 61 :3-29
[6]   GAUSSIAN AND THEIR SUBORDINATED SELF-SIMILAR RANDOM GENERALIZED FIELDS [J].
DOBRUSHIN, RL .
ANNALS OF PROBABILITY, 1979, 7 (01) :1-28
[7]   DETERMINATION OF FRACTAL SCALES ON TRABECULAR BONE X-RAY IMAGES [J].
Harba, R. ;
Jacquet, G. ;
Jennane, R. ;
Loussot, T. ;
Benhamou, C. L. ;
Lespessailles, E. ;
Tourliere, D. .
FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY, 1994, 2 (03) :451-456
[8]   Quadratic variations and estimation of the local Holder index of a Gaussian process [J].
Istas, J ;
Lang, G .
ANNALES DE L INSTITUT HENRI POINCARE-PROBABILITES ET STATISTIQUES, 1997, 33 (04) :407-436
[9]  
JENNANE R, 2001, 18 COLL GRETSI, P99
[10]  
Kahane J.-P., 1985, Cambridge Studies in Advanced Mathematics, VSecond