Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Simple algorithm and color space to generate diverse skin tones

toneyalexander.github.io

Post reply on HN
Print view View original

101–110 of 129 posts

Re: Show HN: Simple algorithm and color space to generate diverse skin tones

#101

Post by itishappy »

zild3d wrote: post #63
s1mon wrote: post #54

It's always entertaining to try to understand these things from first principles. Color and skin color in particular are very complex things to measure and model. It's not just a physical quantity, it's also a matter of human perception based on lighting and a host of factors. It seems like some work was done to research existing approaches, but I don't see any reference to Pantone Skin Tones [0]. Without intending t…

well its not a free as in beer color space

Pantone is not a color space. They are a supplier of physical color samples. Most pigments can be represented in a color space, but that representation differs based on illumination so it not unique. Some Pantone pigments, fluorescent colors in particular, cannot be represented by a color space at all!

Re: Show HN: Simple algorithm and color space to generate diverse skin tones

#103

Post by vector_spaces »

dTal wrote: post #53
mhink wrote: post #47

Earlier quoted context omitted.

Oh man, that's a blast from the past, I think I had that book! Was that the one with an aluminum cover?

That's it! They (rather dubiously) claimed it came from a recycled Russian coke can, if I recall.

I had that one too. I remember I used to crunch on the rice from the bag it came with (I was like 8).

Re: Show HN: Simple algorithm and color space to generate diverse skin tones

#105

Post by nullsanity »

kazinator wrote: post #104

Feature request: drop-down list of ethnicities, where the selection turns on specific guard rails in the parameter space (or retains full movement of the controls, but scales the values). Or is that too racist for 2026?

[dead]

Re: Show HN: Simple algorithm and color space to generate diverse skin tones

#107

Post by ReactiveJelly »

mhink wrote: post #47
dTal wrote: post #34

Earlier quoted context omitted.

Oh goody, an expert in a question I've always wanted to ask. Once upon a time, I encountered a sort of interactive museum book called "Earthsearch". One of its "exhibits" was a color wheel, made of two spinnable pieces of tinted acetate, that purported to be able to generate any skin tone. I suppose this is three degrees of freedom, since for any position of the two wheels you could access a range of colors around th…

Oh man, that's a blast from the past, I think I had that book! Was that the one with an aluminum cover?

I loved that book! Was it that book or its sister that had an image of the pole and said "Spin the Earth the correct direction"? That and "How Things Work" kicked so much ass

Re: Show HN: Simple algorithm and color space to generate diverse skin tones

#108

Post by lstodd »

BHSPitMonkey wrote: post #83
383toast wrote: post #9

Seems to underrepresent pale skin tone variety

Under-represent relative to what, exactly?

Can't express redhead for example. Redhead being not the hair tone, but the translucency of skin that gives the look.

Re: Show HN: Simple algorithm and color space to generate diverse skin tones

#110

Post by zestyping »

Could you explain the first step, "Manually Labeling Colors ? What did you manually label? I didn't quite follow.

From the way the article is written, it sounds like you presented yourself with a bunch of faces of completely random colours and then manually sorted them into two categories, "plausible skin colour" and "implausible skin colour".

But I feel like I must be misunderstanding, because I don't see why you would do that. Why wouldn't you gather photographs of actual faces and sample colours directly from the photos?

Post reply on HN