BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Naive OCR? - Seb Wills\, Inference Group
DTSTART:20060816T130000Z
DTEND:20060816T140000Z
UID:TALK5138@talks.cam.ac.uk
CONTACT:Ryan Prescott Adams
DESCRIPTION:The ability of a program to 'read' the text displayed by other
  applications can be useful in several situations. Examples include screen
  readers (text to speech systems) for disabled users and general-purpose d
 ocument annotation systems. While some computer applications support acces
 sibility APIs that reveal on-screen text to other applications\, a general
 -purpose system needs to be able to read text from the raw pixel image.\n\
 nThe problem\, then\, is doing "Optical Character Recognition" (OCR) not o
 n scanned images but on screen grabs. In this talk I will explore the prop
 erties of on-screen text and consider whether "screen OCR" could be done u
 sing a naive\, lightweight approach which does not require prior knowledge
  of letter shapes. This is work in progress.\n
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR