BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Automatic Visual Recognition in Natural\, Medical\, and 3D Imagery
  - Jamie Shotton (Microsoft Research Cambridge &amp\; Darwin College)
DTSTART:20100422T120000Z
DTEND:20100422T130000Z
UID:TALK22368@talks.cam.ac.uk
CONTACT:Dr James Kirkbride
DESCRIPTION:In this seminar I will present an overview of some recent adva
 nces in computer vision and machine learning that enable automatic visual 
 recognition of objects and body parts.  In natural photographs\, colour\, 
 texture and context provide powerful cues for segmenting the photo into re
 gions and labelling those regions with learned category labels\, such as p
 erson\, tree\, sky\, etc.  Similar techniques can be applied to medical sc
 ans (MRI or CT scans\, for example) to locate the organs within the body\,
  or to map out the grey and white matter in the brain.  Finally\, I will s
 how how new 3D depth sensing cameras coupled with learned recognition algo
 rithms will enable you to control computer games with your whole body\, wi
 thout having to wear or hold anything special.
LOCATION:Entertaining Room\, Darwin College
END:VEVENT
END:VCALENDAR