It is quite interesting that the faces are still 100% recognizable as the people to my eye, but claimed to be altered such that FR cannot do the same.
Thanks!
It is quite interesting that the faces are still 100% recognizable as the people to my eye, but claimed to be altered such that FR cannot do the same.
Thanks!
Yes, it has to do with how Deep Learning trains its inference engine. Just the slightest coordinated changes can make a big difference!