Maximum likelihood estimator for fractal dimension of fractal signal plus noise

Author

Balghonaim, Adil S. ; Keller, James M.

Author_Institution

Dept. of Electr. Eng., King Fahd Univ. of Pet. & Miner., Dhahran, Saudi Arabia

Volume

1

fYear

1997

fDate

25-28 May 1997

Firstpage

223

Abstract

A maximum likelihood estimator (MLE) is developed for estimating the fractal dimension of single variable fraction Brownian motion (fBm) that was corrupted by additive noise. The procedure involve the construction of signal plus noise model and from the model we derive the likelihood function of the signal plus noise. We then estimate the fractal dimension by maximizing the likelihood function. The MLE was tested on fractal signal plus noise and the result was compared with other fractal dimension estimators such as the Box method which does not handle additive noise. The results shows that the MLE gives better results than the Box method

Keywords

Brownian motion; Gaussian distribution; Gaussian noise; fractals; maximum likelihood estimation; signal processing; Box method; MLE; additive noise; fractal dimension; fractal signal plus noise; likelihood function maximisation; maximum likelihood estimator; single variable fraction Brownian motion; 1f noise; Additive noise; Brownian motion; Covariance matrix; Fractals; Frequency; Gaussian noise; Image motion analysis; Image segmentation; Maximum likelihood estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1997. Engineering Innovation: Voyage of Discovery. IEEE 1997 Canadian Conference on

Conference_Location

St. Johns, Nfld.

ISSN

0840-7789

Print_ISBN

0-7803-3716-6

Type

conf

DOI

10.1109/CCECE.1997.614830

Filename

614830