Title :
Adaptive edge detection in compound Gauss-Markov random fields using the minimum description length principle
Author :
Figueiredo, Mário A T ; Leitão, Joel H N
Author_Institution :
Dept. de Engenharia Electrotecnica e de Comput., Inst. Superior Tecnico, Lisbon, Portugal
Abstract :
Edge location in compound Gauss-Markov random fields (CGMRF) is formulated as a parameter estimation problem. Since the number of parameters is unknown, a minimum-description-length (MDL) criterion is proposed for image restoration based on the CGMRF model
Keywords :
Gaussian processes; Markov processes; adaptive signal detection; edge detection; image restoration; parameter estimation; random processes; MDL criterion; adaptive edge detection; compound Gauss-Markov random fields; image restoration; minimum description length principle; parameter estimation; AWGN; Bayesian methods; Gaussian processes; Image edge detection; Image restoration; Maximum likelihood estimation; Parameter estimation; Signal restoration; Telecommunication computing; Writing;
Conference_Titel :
Information Theory and Statistics, 1994. Proceedings., 1994 IEEE-IMS Workshop on
Conference_Location :
Alexandria, VA
Print_ISBN :
0-7803-2761-6
DOI :
10.1109/WITS.1994.513891
