Wow, source code on Github, MIT licensed!
<a href="https://github.com/quantombone/exemplarsvm" rel="nofollow">https://github.com/quantombone/exemplarsvm</a>
Very nice paper. I am actually working on a project in a similar space using very similar techniques, though emphasis is on speed of matching and retrieval as well as matching the objects in the image rather than the image as a whole. Little early demo here <a href="http://www.youtube.com/watch?v=h3YldXhG3Qc&feature=channel_video_title" rel="nofollow">http://www.youtube.com/watch?v=h3YldXhG3Qc&feature=chann...</a><p>Anyway, great work! The paper was a good read.
That's just brilliant. It reminds me a bit of Microsoft's Photosynth.<p>I think this technique provides a lot of possibilities for future consumers. Maybe in the future you could cross-match your photos with an online database and auto-adjust the color and light balance accordingly.<p>E.g. Let's say you went to visit Machu Picchu on a very cloudy and rainy day. You come home and realize your photos look terrible. You put your photos in a piece of software and match them with an online set of Machu Picchu photos. You click on "auto-adjust" and hey presto, they are transformed in to a set of photos that look perfectly lit and balanced. Or am I just dreaming out loud.
Pretty cool. I'm not super familiar with machine learning but from reading section 2 of their paper it sounds like you need to manually find a matching picture to the one you care about (the single positive) and a bunch of pictures that don't match. Then you run the algorithm and come up with a set of weights.<p>It would be nice if things were more automatic, like if a computer program could decide what features were unique (maybe also through machine learning it could learn that buildings are generally unique and the sky is not).
Very cool. Figure 7 is particularly instructive as to the power of this approach.<p>It would also be interesting to see a comparison of images where the features are less pronounced, e.g., matching landscape images. One can imagine uniform weighting approaches performing better where, for example, color is a more important matching criteria than form/features.