Re:IBM no longer offers general purpose facial recognition o...
by brnt on Tuesday June 09, 2020 @12:29AM
(#23463657)
You keep repeating black faces have lower variance, but you never back this up. Personally I find it a preposterous thesis, I find the opposite to be true. I know for a fact genetic diversity is highest among Africans.
By being so convinced of this without showing any proof you are running to risk of proving the point at the root of this issue: we are not addressing our bias in building the system. Not only in our data, but in your case perhaps even not in our thinking.
Re:IBM no longer offers general purpose facial recognition o...
by centimeter on Tuesday June 09, 2020 @11:58AM
(#23467757)
> I know for a fact genetic diversity is highest among Africans.
This doesn't mean what you think it means. In particular, it does not imply wider phenotypic variance.
Re:IBM no longer offers general purpose facial recognition o...
by brnt on Tuesday June 09, 2020 @02:19PM
(#23469187)
No, but it makes it more likely. Meanwhile, you had a nights sleep and still show us nothing.
Re:IBM no longer offers general purpose facial recognition o...
by cycomanic on Tuesday June 09, 2020 @12:34AM
(#23463678)
You continue to bring this up without evidence. Sounds to me you're just stating your own prejudice see https://en.m.wikipedia.org/wiki/Cross-race_effect
Re:IBM no longer offers general purpose facial recognition o...
by centimeter on Tuesday June 09, 2020 @11:57AM
(#23467751)
I calculated it myself in a CV course in university. The same effect was observed by others. I didn't read it somewhere. This shouldn't surprise anyone - white people have tremendously higher variance in color alone (skin, hair, and eyes).
This isn’t the issue - the issue is lower variance across black faces in any basis.
> your hardware and image processing pipeline relies on color contrast
That is how vision works.