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

51–60 of 129 posts

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

#51

Post by dr_scully »

dTal wrote: post #34
dr_scully wrote: post #23

Earlier quoted context omitted.

If you look at my doctoral thesis, in fact skin colour can be parametrised using melanin and haemoglobin concentration; which it means it is indeed (roughly) two dimensional. This allows you to invert the colour of a pixel and identify someone’s chromophore concentration. This is based on previous work of others cited in the thesis. https://discovery.ucl.ac.uk/id/eprint/10093345/

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…

That’s sounds very interesting. I’m not sure. In the thesis, I generated spectral curves and transformed them using the light and camera sensitivity curves. So, in theory it could be used in any color space.

But I can’t vouch for the accuracy of the book, but I suspect it was an approximation.

The haemoglobin and melanin are roughly in separate layers of the skin. There is an approximation known as Beer-Lambert that models the skin as two semi-transparent layers. This ignores subsurface scattering, but is roughly correct.

So, in theory two acetate sheets might replicate this. That’s my intuitive opinion. It has been many years since I did this work.

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

#52

Post by E-Reverance »

automatoney wrote: post #17
stephantul wrote: post #14

Love it. I especially thought the introspective “aside” section on related resources was great, and I wish more people would show this kind of reflection.

Thanks! I hope to send lots of love those ways, they're basically all things that I found outside of this work that I liked enough to remember (I think Humanae was the one that I found while doing this).

I definitely don't speak for all non-white people when I say this, but personally I find people obsessing over it disturbing/offensive independent of whether their intentions are racist or anti-racist. I did find modeling/data-driven perspective cool though

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

#53

Post by dTal »

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?

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

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

#54

Post by s1mon »

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 to, I've worked on 3 different projects which involved measuring skin tones for makeup applications. The Pantone range is not 100% perfect, but it's pretty well done and easy to understand. There are two axes: a light/dark one, and red-yellow one [1].

[0] https://www.pantone.com/na/en-us/skintone

[1] https://cosmeticsbusiness.com/pantone-skintone-guide-80945

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

#55

Post by iwontberude »

Joel_Mckay wrote: post #44
GolDDranks wrote: post #26

Earlier quoted context omitted.

I've heard that the so-called "yellowish" skin color that non-tanned East Asians tend to have, is due to relative abundance of subcutaneous fat. If that's true, is that captured by the haemoglobin dimension or is it a yet another degree of freedom?

All skin is slightly translucent, and color/tones forms a gradient across the surface of the skin. Your upper cheeks and forehead are usually slightly reddish, and the chin/neck are slightly bluish. People only turn yellow if they have kidney or liver damage. However, some distinctive features like Lucy Liu's natural freckles are tough to draw right. We looked around a lot for a procedural texture/shader to help make…

> People only turn yellow if they have kidney or liver damage.

This is not true. Roughly 5% of people have Gilbert's Syndrome which is genetic, metabolic abnormality where the bilirubin from dead blood cells are conjugated slower than the baseline patient leading to yellowing of the skin. It is not due to liver damage or disease and is a benign condition. Not to mention there is carotenemia from eating too many carrots or squash -- again not kidney/liver damage related.

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

#60

Post by barbecue_sauce »

xp84 wrote: post #38

This part ( https://toneyalexander.github.io/inclusive-color-space/#pick... ) is especially cool. Would love to see this 3-D picker ability in the many character designers out there, instead of the lame 8 swatches or whatever.

I think the ideal would be to use this picker to select a few tones, and then gradient map those across different parts of the body according to a grayscale map. Then you could fine-tune things like palm color, cheeks, facial tone, etc. individually.
Post reply on HN