0411162 20240103182306.320060210235959.9 953-184-061-X 1 Rome University of ROMA TRE 2003 6 s. 332-337LončaricS.NeriA.BabicH. multichannel blind deconvolution total variation MAP estimation cav_un_auth*0101209 Šroubek Filip UTIA-B Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101087 Flusser Jan UTIA-B Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/prace/20030149.pdf 09K GA102/00/1711 GA ČR cav_un_auth*0004052 GA201/03/0675 GA ČR cav_un_auth*0001807 CEZ:AV0Z1075907 Existing multichannel blind restoration techniques are prone to noise, assume perfect spatial alignment of channels and a correct estimation of blur size. We develop an alternating minimization scheme based on maximum a posteriori probability estimation with a priori distributions derived from the multichannel framework and from the variational priciple. We observe that the exact knowledge of the blur size is not necessary and that translation misregistration can be automatically removed. cav_un_auth*0213089 ISPA 2003 /3./ Rome IT 18.09.2003-20.09.2003 BD ZOI http://hdl.handle.net/11104/0131248 UTIA-B 20030149 2003 2003 Rome University of ROMA TRE 953-184-061-X Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis 332 337 Lončaric S. 340 Neri A. 340 Babic H. 340