Google Search By Image

Re:Google Search By Image by antihero on Tuesday June 14, 2011 @01:46PM (#2653947)

I wonder how it'll compare with TinEye.

[ Parent | on HN ]

Re:Google Search By Image by tropin on Tuesday June 14, 2011 @02:34PM (#2654141)

Easy, indepently of how good is, just trying to fight against Google resources will crush TinEye. Today must be a terrible day for them.

[ Parent | on HN ]

Re:Google Search By Image by guyzero on Tuesday June 14, 2011 @06:24PM (#2655036)

Idee's business model has little to do with TinEye. They're probably not very worried.

[ Parent | on HN ]

Re:Google Search By Image by ratzinho87 on Tuesday June 14, 2011 @06:26PM (#2655044)

The article said the technology is very similar to Google Goggles. From what I could deduce, Goggles uses some kind of local invariant descriptors (like SIFT or SURF), and TinEye uses some kind of global descriptor (maybe something like this: http://www.hackerfactor.com/blog/index.php?/archives/432-Loo... ).

If that is right, Google will be able to retrieve different photos in which the same object appears, whereas TinEye only retrieves the same image, with or without some changes. So, they're quite different beasts.

Can't wait to see if I am right...

[ Parent | on HN ]

Re:Google Search By Image by pixcavator on Tuesday June 14, 2011 @07:09PM (#2655217)

Actually, TinEye is pretty good at partial matching.

[ Parent | on HN ]

Re:Google Search By Image by krisw on Tuesday June 14, 2011 @07:18PM (#2655248)

I compared/contrasted TinEye against Google CBIR for a bunch of images (I use TinEye a lot) and I have to say TinEye looks better than Google CBIR so far. TinEye has less "zero results" and more search results overall, I get the feeling TinEye deals with "Photoshopped images" better somehow.

[ Parent | on HN ]