They also use image recognition to detect nudity and previously classified child porn.
If you can do this (with different categories, for instance, determining what is nudity, then determining black people, to automatically classify porn with black actors automatically), it would be quite impressive. Results have nearly 5% error on CIFAR-10, which is full of clearly distinct categories - planes versus boats.
Not only impressive, but likely very profitable.
> Results have nearly 5% error on CIFAR-10
Any idea what the error rate is for human classification on CIFAR-10 images?
https://en.m.wikipedia.org/wiki/List_of_file_signatures
Also check out "libmagic"