…we’ll know we’re close to cracking the Turing Test. For now, here’s Tiltomo, another proof of concept visual engine, courtesy Silicon Beat.
When A Visual Search Engine Is No Longer “Proof of Concept…”
…we'll know we're close to cracking the Turing Test. For now, here's Tiltomo, another proof of concept visual engine, courtesy Silicon Beat….
Well, I have to admit, this search engine is interesting. I like the photos as I have spent a lot of time, on and off, around the World Trade Center, though much less after 9/11.
I wonder how this search engine works – does it use the tagging and metadata in the source code?
In answer to how Tiltomo works?… Our Visual Search calculates separately both Color & Texture in varying amounts to determine what we call “Visually Similar”. “Visually Similar” can be very subjective. For this reason we have two Visual Search modes. The first is “100% Color / Texture”; this matches images that are “similar” in terms of only Color / Texture. Our second mode “Theme” uses Color / Texture and also takes Visual Context into consideration. This mode is most likely to match images that have a Visual / Contextual relationship.
Soon we will add a slider that allows the user to change the balance between Color / Texture & Context.
The slider sounds cool. Will it filter results on the fly, or tune the search query prior to it’s completion?
you coul also try cortina, visual search, we did that in 2003
http://www.cortina.ch
Maybe Cortina would be cool too, if it returned any results at all.
I received this message 3 consecutive times from Cortina searches:
“Results 0 to 12 of about 0 Search took 0.041 seconds”
The slider will reprocess the results on the fly. Drop me an email and I can give you pre-beta access.