Title :
Image blur identification by using higher order statistic techniques
Author :
Xu, You ; Crebbin, Greg
Author_Institution :
Dept. of Electr. & Electron. Eng., Western Australia Univ., Nedlands, WA, Australia
Abstract :
In this paper, higher order statistic (HOS) based blur identification methods are proposed to estimate blur coefficients in image restoration, in which the image is considered as a colored process. One dimensional (1-D) based blur identification algorithms are proposed, and their extensions to two dimensional (2-D) cases are discussed. The experimental results are presented to demonstrate the performance of the proposed methods in this paper
Keywords :
higher order statistics; image recognition; image restoration; spectral analysis; colored process; higher order statistic techniques; image blur identification; image restoration; one dimensional cases; performance; two dimensional cases; Autoregressive processes; Data mining; Degradation; Frequency domain analysis; Gaussian distribution; Higher order statistics; Image restoration; Maximum likelihood estimation; Probability density function; System identification;
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
DOI :
10.1109/ICIP.1996.560373
