Get FREE lessons from "Hack It Easy Hacking Course"

Enter your email and instantly receive the lessons in your inbox for free

Tuesday, October 14, 2008

Search photos based on content

Soon you will be able to search photos through their content. It is not like searching keywords on google. But content of pictures. Like faces, buildings, woman, food etc. A pair of Penn State researchers has come up with a statistical approach that may one day make Internet searches for photographs quite easier.
You can too see a demo here. Visit and improve this technology http://www.alipr.com/.


The tool they use for this purpose is called Automatic Linguistic Indexing of Pictures in Real-Time (ALIPR), which works by teaching computers to recognize the contents of photographs, such as buildings, people, or landscapes.The procedure is very different from searching for keywords in the surrounding text, as is done with most current image-retrieval systems.The team recently received a patent for an earlier version of the approach called ALIP, and is in the process of obtaining another patent for the more sophisticated ALIPR.

It is good but need to be improved a lot. It currently shows images from flickr.

We then would build a statistical model to teach the computer to recognize patterns in color and texture among these 100 photos and to assign our keywords to new photos that seem to contain national parks, landscapes, and/or trees. Eventually, we hope to reverse the process so that a person can use the keywords to search the Web for relevant images.


0 comments:

x

   First Name:
* Your Email Address:
 

Share

Twitter Delicious Facebook Digg Stumbleupon Favorites More