Title :
Data-driven restoration of degraded binary MRF images using EM method
Author :
Yamazaki, Tatsuya ; Shirazi, Mehdi N. ; Noda, Hideki
Author_Institution :
Minist. of Posts & Telecommun., Kobe, Japan
Abstract :
A data-driven restoration algorithm is developed for binary images degraded nonadditively with flip noises. The true image is assumed to be a realization of a Markov random field (MRF), and the nonadditive flip noises are assumed to be statistically independent and asymmetric. The parameter estimations of the noise and the true image are carried out iteratively in the context of an expectation and maximization (EM) procedure by approximating Baum´s auxiliary function of the EM procedure. To approximate Baum´s auxiliary function, the estimate of the true image at each EM iteration is used. Simulation examples show the effectiveness of the data-driven restoration algorithm and the parameter estimation procedures
Keywords :
Markov processes; image reconstruction; noise; parameter estimation; Baum´s auxiliary function; EM method; data-driven restoration algorithm; degraded binary Markov random field images; expectation and maximization procedure; iterative process; nonadditive flip noises; parameter estimation procedures; statistically independent asymmetric flip noises; Colored noise; Degradation; Image restoration; Iterative algorithms; Iterative methods; Lattices; Layout; Markov random fields; Maximum likelihood estimation; Parameter estimation;
Conference_Titel :
TENCON '92. ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' 1992 IEEE Region 10 International Conference.
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-0849-2
DOI :
10.1109/TENCON.1992.271860
