cc-archive / open-ledger

Prototype code and examples for work on the Creative Commons "CC Search" project
MIT License
48 stars 23 forks source link

Consider mechanisms to identify reused works #15

Open lizadaly opened 8 years ago

lizadaly commented 8 years ago

Identifying near-identical images is the goal of #5, but what about reuse that's quite transformative and not subject to identification by automated processes?

I typed my Flickr handle into the prototype search box and found reuse of one of my CC-licensed photos that I didn't know about (cool!): https://www.flickr.com/photos/53133240@N00/5051004716

Then I tried searching for the part of a Flickr URL up to my username (www.flickr.com/photos/lizadaly/) and found another that way: https://www.flickr.com/photos/93211492@N06/8478352802

(That URL search query gives spurious results from 500px, though.)

Though identifying derivative works is not a priority for this part of the project, evaluating techniques could be instructive.