1–10 of 22 posts
Show HN: Type in a search to find the average of the first 50 image results
imgessence.com
Circle: http://imgessence.com/browse/view/329
Benzene: http://imgessence.com/browse/view/303
Nike logo: http://imgessence.com/browse/view/299
These are the best ones I've managed to create so far: Circle: http://imgessence.com/browse/view/329 Benzene: http://imgessence.com/browse/view/303 Nike logo: http://imgessence.com/browse/view/299
Face: http://imgessence.com/browse/view/29
Spirit: http://imgessence.com/browse/view/510
It works best on symmetric, concrete objects.
This is the problem with services this fun to play with. Here at HN we break our toys!
Spoon is an interesting example : http://imgessence.com/browse/view/190 - You can see the many basic outlines of a 'spoony' shape. However, all of those images of spoon are presenting the object rotated at some more or less random angles. It would be interesting to add some algorithm that would try to match the images (rotate / scale) to the average and hence give less noisy output.
I'm struggling to see why this is interesting.
Added in edit: Rather than just downvoting, perhaps you could tell my why this is interesting. Were there technical challenges to overcome? If so - what? What did the implementor learn by doing this? What are you learning by using it? Please - help me to see why this is at all interesting! I genuinely don't understand.