DocumentCode :
290249
Title :
Periodicity estimation in textured images using to ML approach
Author :
Marques, Jorge S.
Author_Institution :
INESC, Tech. Univ. Lisbon, Portugal
Volume :
v
fYear :
1994
fDate :
19-22 Apr 1994
Abstract :
In the analysis of quasi-periodic textured images, good estimates of the periodicity parameters art instrumental to obtain an accurate evaluation of the texel characteristics. This paper presents a maximum likelihood algorithm for the estimation of periodicity parameters from the peaks of the localized Fourier spectrum. To derive the ML estimator, a stochastic model of the spectral peaks is required. Therefore, a probability model which incorporates false alarms, detection errors as well as random jitter in frequency estimates is described in this paper. The relationship between the ML algorithm proposed in this paper and the Hough transform is addressed. Finally, experimental tests with synthetic and natural images are presented to assess the performance of the ML estimator
Keywords :
Fourier analysis; Hough transforms; frequency estimation; image texture; jitter; maximum likelihood estimation; probability; spectral analysis; stochastic processes; Hough transform; ML estimator; detection errors; experimental tests; false alarms; frequency estimates; localized Fourier spectrum; maximum likelihood algorithm; natural images; performance; periodicity parameters estimation; probability model; quasi-periodic textured images; random jitter; spectral peaks; stochastic model; synthetic images; Art; Frequency estimation; Image analysis; Image texture analysis; Instruments; Jitter; Maximum likelihood detection; Maximum likelihood estimation; Parameter estimation; Stochastic processes;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on
Conference_Location :
Adelaide, SA
ISSN :
1520-6149
Print_ISBN :
0-7803-1775-0
Type :
conf
DOI :
10.1109/ICASSP.1994.389519
Filename :
389519
Link To Document :
بازگشت