Title :
Image coding over real/complex fields: parameters estimation of nearly nonstationary AR(p) models
Author_Institution :
Dept. of Commun. & Inf. Syst., Univ. of Split, Croatia
fDate :
29 Jun-4 Jul 1997
Abstract :
The AR parameter estimation problem is considered under noisy conditions concerned with the decoding of BCH codes over real/-complex fields. Autoregressive parameter distribution based on the parameter covariance matrix is analyzed. This distribution defines the code ability to correct the impulse noise in spectral coefficients corrupted by white noise
Keywords :
BCH codes; autoregressive processes; covariance matrices; decoding; image coding; parameter estimation; spectral analysis; white noise; AR parameter estimation problem; BCH codes; autoregressive parameter distribution; complex fields; decoding; image coding; impulse noise; nearly nonstationary AR(p) models; noisy conditions; parameter covariance matrix; real fields; spectral coefficients; white noise corruption; Covariance matrix; Decoding; Discrete Fourier transforms; Discrete cosine transforms; Equations; Frequency domain analysis; Galois fields; Image coding; Noise level; Parameter estimation;
Conference_Titel :
Information Theory. 1997. Proceedings., 1997 IEEE International Symposium on
Conference_Location :
Ulm
Print_ISBN :
0-7803-3956-8
DOI :
10.1109/ISIT.1997.613386
