[dave84]

Sounds impressive. Do you have a pre-existing product database that you match them up to or do you just create products on the fly?

[tedmiston]

I would strongly guess it's a fixed set of product images they're training against, possibly attained by massive scraping. Another part of training or processing might consist of a reverse image search API, like TinEye, and gathering metadata from the pages containing the result images.

[ericgoldberg]

We do our own searching and wrote our own crawlers. Does that answer your question?

[dave84]

It does indeed. I'm very impressed. Keep up the good work!