BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Signal Processing and Communications Lab Seminars
SUMMARY:Hyperanalytic Denoising - Sofia Olhede\, Dept. of
Mathematics\, Imperial College London
DTSTART;TZID=Europe/London:20070412T130000
DTEND;TZID=Europe/London:20070412T140000
UID:TALK6713AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/6713
DESCRIPTION:Image estimation requires a compromise between rec
onstruction flexibility and computational tractabi
lity. A commonly adopted approach to the estimatio
n problem is to decompose the observed image in a
suitable basis\, where the compression of the deco
mposition simplifies subsequent analysis. Much eff
ort has been expanded in designing appropriate 2-D
decompositions\, but of great importance is also
the statistical estimation procedure chosen\, and
this talk will focus on the estimation of any set
of decomposition coefficients.\n\nA new estimation
method that can be combined with a local decompos
ition method is introduced. Under the assumption t
hat structured features correspond to highly conce
ntrated and connected regions of the spatial and s
patial frequency space additional image replicates
with the same local structure as the observed ima
ge are constructed from the observed image. The de
composition of the image is estimated not only usi
ng the observed image decomposition coefficients\,
but also using a set of local coefficients constr
ucted from the replicate images. Given the tractab
le form of the first and second order structure of
the full set of decomposition coefficients of bot
h the image and replicate images at any given scal
e and spatial position\, the full procedure can be
specified analytically\, and its risk calculated
explicitly. The proposed method is implemented on
several examples\, and theoretical risk calculatio
ns substantiated\, as well as visually appealing r
econstructions presented. \n\nThe slides of the se
minar are available at\nhttp://stats.ma.ic.ac.uk/s
co/public_html/seminarsIC.htm\n\nThis work was par
t of an EPSRC supported project.
LOCATION:LR5\, Engineering\, Department of
CONTACT:Taylan Cemgil
END:VEVENT
END:VCALENDAR