BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computer Vision Systems for Real-World Use - Cecily Morrison\, Mic
 rosoft Research Cambridge
DTSTART:20150521T101500Z
DTEND:20150521T111500Z
UID:TALK59514@talks.cam.ac.uk
CONTACT:Alan Blackwell
DESCRIPTION:The use of depth-sensing computer vision to capture bodily mov
 ement and gestures is increasingly being exploited in healthcare. Yet\, th
 ere are few descriptions of how real-world practices and usage influence t
 he design and development of such applications. To this end\, we present t
 he development and empirical evaluation of ASSESS MS\, a system to support
  the clinical assessment of Multiple Sclerosis (MS) using Kinect. A key is
 sue for developing machine-learning based systems is the need for standard
 ized data on which statistical inferences can be made. I will demonstrate 
 that there are many aspects of real clinical practice that are at odds wit
 h the need to capture standardized data for a computer vision system. I wi
 ll then draw out the importance of providing tools to help users to see wh
 at the camera "sees" as a way to achieve standardized data\, while maintai
 ning the social interaction of an assessment.
LOCATION:Rainbow Seminar Room (SS03)\, Computer Laboratory
END:VEVENT
END:VCALENDAR