BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Restoration of images with blur and noise - effective models for k
 nown and unknown blurs - Chen\, K (University of Liverpool)
DTSTART:20140207T153000Z
DTEND:20140207T160000Z
UID:TALK50705@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:In recent years\, the interdisciplinary field of imaging scien
 ce has been experiencing an explosive growth in active research and applic
 ations.\n \nIn this talk I shall present some recent and new work of model
 ing the inverse problem of removing noise and blur in a given and observed
  image. Here we assume the Gaussian additive noise is present and the blur
  is defined by some linear filters. Inverting the filtering process does n
 ot lead to unique solutions without suitable regularization. There are sev
 eral cases to discuss:\n\nFirstly I discuss the problem of how to select o
 ptimal coupling parameters\, given an accurate estimate of the noise level
 \, in a total variation (TV) optimisation model.\n\nSecondly I show a new 
 algorithm for imposing the positivity constraint for the TV model for the 
 case of a known blur.\n\nFinally I show how to generalise the new idea to 
 the blind deconvolution where the blur operator is unknown and must be res
 tored along with the image. Again the TV regularisers are used. However wi
 th the splitting idea\, our work can be extended to include other high ord
 er regularizers such as the mean curvature.\n\nOnce an observed image is i
 mproved\, further tasks such as segmentation and co-registration become fe
 asible. There will be potentially ample applications to follow up.\n\nJoin
 t work with B. Williams\, J. P. Zhang\, Y.Zheng\, S. Harding (Liverpool) a
 nd E. Piccolomini\, F. Zama (Bologna). Other collaborators in imaging in g
 eneral include T. F. Chan\, R. H. Chan\, B. Yu\, N. Badshah\, H. Ali\, L. 
 Rada\, C. Brito\, L. Sun\, F. L. Yang\, N. Chumchob\, M. Hintermuller\, Y.
  Q. Dong\, X. C. Tai\, etc.\n\nRelated Links: http://www.liv.ac.uk/~cmchen
 ke - Home page\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR