BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The big picture - mining millions of images - Dr Chris Town\, Camb
 ridge University Computer Laboratory
DTSTART:20081112T130000Z
DTEND:20081112T140000Z
UID:TALK15153@talks.cam.ac.uk
CONTACT:11123
DESCRIPTION:Traditional search engines such as Google are only capable of 
 indexing and searching text\, yet about 73% of the data on the web consist
 s of images and video. Meanwhile\, consumers and businesses are accumulati
 ng millions of digital photos\, yet they lack efficient tools to browse\, 
 organise\, search\, and retrieve them.\n\nTo address these challenges\, my
  colleagues and I have developed a content based image retrieval methodolo
 gy that enables computers to automatically index and search images by visu
 al content. The system features a range of image processing and analysis m
 odules which can automatically recognise semantic image content (e.g. beac
 hes\, sky\, faces etc.). It allows ordinary users to intuitively search fo
 r pictures using text queries consisting of keywords or short natural lang
 uage sentences\, which are then linked to image content using an ontology 
 of visual concepts.\n\nHowever\, with an estimated 15 billion images avail
 able on the internet today\, there is great need for technologies to provi
 de the scalable computing resources required to process such vast quantiti
 es of data. With the help of funding from the UK STFC and in collaboration
  with the Cambridge University eScience Centre\, I am developing technique
 s to scale my image analysis approach to millions of digital pictures usin
 g distributed grid processing technology. This was done by porting the sof
 tware to the middleware architecture deployed on the UK particle physics g
 rid\, which consists of several 10s of thousands of computers. We are also
  furthering middleware and user interface development to make it easier fo
 r other non-physics applications from academia or industry to make use of 
 grid computing.\n
LOCATION:Combination Room\, Wolfson College
END:VEVENT
END:VCALENDAR