[pHash-support] Announcement for Open Source Video project

[Sebastian Gallese]

I set up some initial documentation and video for a project I'm
titling Open Source Video.  Here's the tagline of the project:

"Open Source Video is a software project that attempts to translate
motion picture files into Creative Commons licensed movies. Open
Source Video treats a standard QuickTime movie file as a series of
moving images. Then, by using the open source image recognition
software known as pHash, Open Source Video tries to compare each frame
of an "original" video to a database of Creative Common's photos
downloaded off of Flickr"

You can see some test videos and basic documentation of the project goals here:
https://wiki.brown.edu/confluence/display/mcm1700n/Open+Source+Video

If anybody has any suggestions on how to better use pHash for such a
project, I'd love to hear suggestions, criticisms, or comments.  If
you see any technical errors in my description, let me know!

Right now, since I could not get pHash MVP trees to work in Java on
large databases, I compare every hashed image in one folder to every
other hashed image in another folder and find the lowest MH image
distance between these two hashed images.  You can see my code here
for those of you looking to use an alternative to MVP trees in Java.
Right now, it takes about 15 minutes to hash 1000 images of around
150KB on my MacBook 2.0GHz.

Here's the code:
http://gist.github.com/316013

Thanks,
Seb