THREE-DIMENSIONAL IMAGE RESTORATION USING ARMA MODELLING AND ML ESTIMATION.

Tzafestas, SG; Angelleli, A-M

dc.contributor.author	Tzafestas, SG	en
dc.contributor.author	Angelleli, A-M	en
dc.date.accessioned	2014-03-01T02:47:45Z
dc.date.available	2014-03-01T02:47:45Z
dc.date.issued	1985	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33314
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0022237512&partnerID=40&md5=896f533cb31c73b4b542b0ec48e1d4dd	en
dc.subject.other	SIGNAL FILTERING AND PREDICTION	en
dc.subject.other	AUTOREGRESSIVE MOVING-AVERAGE PROCESSES	en
dc.subject.other	IMAGE RESTORATION	en
dc.subject.other	MAXIMUM-LIKELIHOOD ESTIMATION	en
dc.subject.other	IMAGE PROCESSING	en
dc.title	THREE-DIMENSIONAL IMAGE RESTORATION USING ARMA MODELLING AND ML ESTIMATION.	en
heal.type	conferenceItem	en
heal.publicationDate	1985	en
heal.abstract	Most recursive image enhancement-restoration techniques are based on the assumption that the autocovariance function of the original noise-free image is known or can be estimated beforehand. Recently, T. Katayama (1979) developed a technique that bypasses this assumption by using an ARMA model of the 2-D image field, combined with maximum-likelihood (ML) parameter estimation and appropriate filtering. Katayama's technique is here extended to 3-dimensional (volume) image fields, which are encountered in many practical situations. Some digital simulation results have been derived for artificial 3-dimensional fields, showing the feasibility of the method.	en
heal.publisher	IEEE, New York, NY, USA	en
heal.journalName	[No source information available]	en
dc.identifier.spage	227	en
dc.identifier.epage	232	en