Live data from Hacker News

Genetic mugshot recreates faces from nothing but DNA

newscientist.com

21–26 of 26 posts

Re: Genetic mugshot recreates faces from nothing but DNA

#21
post #4

This is more like a facial composite[1] than a mug shot[2]. A mug shot is a photo of an identified person. A facial composite is a synthetic graphic of an unidentified person. The distinction is important because a facial composite is an investigative tool use to identify a suspect, and a mug shot is not. [1] https://en.wikipedia.org/wiki/Facial_composite [2] https://en.wikipedia.org/wiki/Mug_shot

New Scientist is a British magazine, but 'mug shot' isn't an everyday term in the UK (partly because UK police don't automatically release photos of arrestees like most US police), so over there the term is used a bit more loosely.

Re: Genetic mugshot recreates faces from nothing but DNA

#22
post #8

"One day, the technique may even allow us to gaze into the faces of extinct human-like species that interbred with our own ancestors." I don't know how accurate that statement is. They can predict human faces because they can look at examples of DNA and the paired human face, they would have to use unsupervised machine learning for extinct species and have no real way to validate it.

If you developed it to give consistently good results on other primates and then other mammals, then you could probably feel pretty confident about things such as cranial shape, eye color etc. etc.

Re: Genetic mugshot recreates faces from nothing but DNA

#23
post #8

"One day, the technique may even allow us to gaze into the faces of extinct human-like species that interbred with our own ancestors." I don't know how accurate that statement is. They can predict human faces because they can look at examples of DNA and the paired human face, they would have to use unsupervised machine learning for extinct species and have no real way to validate it.

This is possible as the molecular machinery for translating a DNA sequence into a 3-D structure is highly conserved - basically if you can convert modern human DNA into a face then you can convert other close relatives as well.

Re: Genetic mugshot recreates faces from nothing but DNA

#24
post #8

"One day, the technique may even allow us to gaze into the faces of extinct human-like species that interbred with our own ancestors." I don't know how accurate that statement is. They can predict human faces because they can look at examples of DNA and the paired human face, they would have to use unsupervised machine learning for extinct species and have no real way to validate it.

If you developed it to give consistently good results on other primates and then other mammals, then you could probably feel pretty confident about things such as cranial shape, eye color etc. etc.

We could probably feel pretty confident about eye color right now. What color are gorilla eyes? Howler monkey eyes? Humans barely vary in eye color at all; fancy European eye colors are a very recent phenomenon.

Re: Genetic mugshot recreates faces from nothing but DNA

#26

It would be helpful to see more validation examples like the photograph of the former New Scientist reporter shown with the article. I wonder how we would judge the resemblance if the photographs hadn't shown the additional gray outline (complete with earring in the same design!) with the computer-generated images. I know plenty of examples of people from the same family lineage (siblings or first cousins) who grew u…

My work primarily based around 3D reconstruction of human faces from photos. It's a machine learning problem, and we have quite good results at www.3D-Avatar-Store.com. I have personally performed thousands of 3D reconstructions of people, and have developed a pretty good intuitive sense about a person from their facial photo.

Of particular interest has been reconstructing twins and near age siblings at different points in their lives. From my experience, the strongest drivers of facial appearance I've found are, in order:

1) genetics & ethnic background 2) attitude (not life style, but life perspective) 3) life style

In #1, I see very little variation between children of similar ethnic backgrounds. And when I say "little variation", I mean in the formal sense, from the facial recognition coefficients. Children are interesting in their facial photos often clearly indicate how they will progress through #2.

I'm yet to read formal observations of my #2; It is very clear to me when creating reconstructions of real people, it is their "attitude" they wear on their face day after day that by the time an individual reaches adulthood that "look" is impressed on their face. And this "look" tends to increase over time and age, unless a major attitude adjustment takes place.

I see #3 as a strong influence to facial appearance, but it is driven by #2, so I consider attitude to be the #1 driver of facial appearance which an individual can have control over (short of surgery).

Post reply on HN