The Collaborative Imaging Grid

1
The Collaborative Imaging Grid
A collaborative research environment enabling
Researchers to learn from images when computer
vision cannot

• Paul Javid, Kurtis Heimerl

2
What is the problem with computer vision?

• Computer Vision is getting better at seeing
  patterns in images
• Face Recognition for Security (Is this person
  Kurtis?)
• Traffic Monitoring (Are there many cars on the
  road?)
• But we are no where near the capabilities of
  the human eye!
• Medical research (Does this lung have lung
  cancer?)
• Spyware detection (Is this image spyware?)
• Requires Human Pattern Recognition!

3
The Solution

• Create a research tool allowing researchers to
  aggregate human knowledge about
  digital images.
• Images are coupled with metadata
• Metadata contains additional information about
  the images
• Researchers have access to database which
  contains all images and their coupled metadata
• Creates the world-wide-web of human knowledge
  about images.

4
Example application scenario

• 100 Cancer Researchers have knowledge about
  what a cancerous lung looks like.
• In order for such information to be shared
  ubiquitously
• When researcher identifies cancerous lung image,
  they add that image and its metadata to database
• Metadata contains information about patient
  history, age, etc.
• Researcher then may analyze other images and
  contribute to their metadata
• Allows other researchers to search, group, edit,
  and categorize images in database based on their
  metadata, thereby furthering cancer research

5
How are we going to do this?

• Clients have access to database via a
  web-browser.
• Outputs DHTML
• Server side uses GNUs Tomcat webserver and the
  Spring Framework.
• Toolkits implemented in Java!
• Metadata stored as XML files.
• Velocity toolkit to generate HTML for client
• Clients log in via web browser to Tomcat
  webserver which contains database of images and
  coupled metadata (XML Files). Server exports
  HTML for clients viewing

6
Conclusion

• Obvious demand for Collaborative Imaging Grid in
  various disciples - biotechnology, computer
  vision, etc.
• Easy to Implement
• Well known implementation language (Java)
• Easy integration between XML metadata,
  webserver, and client side browser.
• We have done this before!