http://www.studio360.org/2013/feb/08/making-portraits-out-of-dna/

I received an anonymous sample of hair, and made a portrait of this person’s DNA – see the results below!

Kurt Anderson’s DNA Portrait (age 25)
Photo by Julia Lowrie Henderson + Montage by Stefan Sierhej

It’s open tues-fri noon to 5pm.

Lots of great press for the project in the past week:

Studio 360 radio show
Dan Rather Reports
Boston Globe
The Creators Project
Designboom

I am excited to participate in the Eyebeam annual showcase, opening Thursday! They are moving from a twice a year open studios show to a once a year retrospective of the work of residents and fellows from the past year. It is a great group of artists and looks like it will be a fantastic show.

I will be showing the latest developments in my Stranger Visions project, unveiling the first portrait derived from found material as well as a video documenting the process.

I will also be joining Eyebeam fellow Mark Shepard and curator Deborah Fisher from A Blade of Grass in a conversation about art and politics, idealism and ideas of progress on a panel this Saturday.

WELL it was quite an ordeal installing my collaboration with video installation artist Adriana Varella Unlanguage but in the end we did it, and it looks fantastic. (picture coming soon…) We exhibited in the Zamek – a sort of pretend castle built just 100 years ago and home to Hitler’s cabinet during WWII – an artist actually made a site-specific piece for Hitler’s office that involved freezing a giant sheet of water and ash but appropriately the power went out and the ice melted and ended up destroying the room. A fitting fairwell to Hitler’s office I think although the Biennale staff were not so happy about it! More about the surprisingly interesting zamek on wikipedia.

The piece is something I am thinking of as a kind of finale to the body of work I have been experimenting with the past 9(!) years addressing language in various forms. The works in the series begin with Netlingua, my Bennington undergraduate thesis project and continue to Listening Post, Totem, Jaaga Dhvani and finally Unlanguage.

The piece is interactive. Two computer terminals encourage gallery-goers to enter the first word that comes to their mind. When a new word is entered a poem is generated using these two inputs as seeds. The poem grows and branches showing the permutations and possibilities native to the Bayesian model underpinning the program. Each time a new poem is formed the previous poem begins to mutate and eventually self-destruct and fade away.

Here is a video that gives a sense of what this looks like:

I’m sure that I will continue to work with language ( I have a dissertation to write after all!) but right now I feel ready to move on to a different frame of reference and some new ideas… more on new ideas soon!

Facing the Genetic Future

Sitting in a therapist’s office, New York City artist Heather Dewey-Hagborg discovered a hair

lodged in a crack in the glass covering a painting on the wall. “I stared at it for an hour,”

she says. “I couldn’t stop wondering who it belonged to, and what I could find out about

that person.”

After reading a story in Science about the new field of forensic DNA phenotyping

(18 February 2011, p. 838), Dewey-Hagborg decided to turn her fascination into an art

project. She collected 11 hairs left around the city by strangers and learned how to test their

DNA at a genetics lab. Now, she’s printing three dimensional masks, or approximations, of those

people’s faces, which will be on display—along with her own—in a January exhibition called Stranger

Visions. The masks reflect eye color, geographical roots, sex, and other traits, but not exact facial

features because forensic phenotyping can’t fill in all the details. But it might one day, and with ever

cheaper sequencing, an era of “genetic surveillance” is looming, says Dewey-Hagborg. “As a society, we

need to have a discussion about that.”

I downloaded his file and ran it through my Stranger Visions software today to generate my take on his face. You can see a side by side comparison of my generated face and his actual face (well pulled from google image search results) below.

I have worked with facial recognition algorithms in the past and one technique I had read about was the use of a morphable 3d facial model to attempt to recognize faces at weird angles. As I have previously turned systems like this, intended for surveillance, into systems for creativity, it naturally occurred to me that the same system could be used to generate faces. And if you can determine what correlates certain types of faces you can then generate faces with those characteristics using principal components analysis.

It turns out the research group behind the Basel Morphable Model realized this as well and after much digging I figured out how to use their matlab model as a starting point for many different types of parameters. They had already found the primary axes for gender, age and weight so the main parameter missing was ethnicity.

The issue here of course is that all these models are heavily skewed towards people of european descent so I knew from the beginning that I would have to deal with significant inductive bias. For those who have never read AI textbooks, inductive bias describes the set of assumptions a programmer makes in the design of a machine learning system. Or as Luger puts it in Artificial Intelligence “Inductive bias refers to any criteria a learner uses to constrain the concept space or select concepts within that space”. It is actually a pretty fascinating subject in its own right that dates back to the origins of inductive logic with Aristotle. The basic idea is that by looking at a certain number of examples of something we can form generalization about all things of this type. Now we all know what happens when we make assumptions based on limited experiences, so the flaws of inductive reasoning are pretty obvious. Then again, all reasoning rests on making some initial assumptions (otherwise we have nothing to deduce from!) so at the end of the day some amount of induction is unavoidable. For more on induction, deduction and their interdependence see Hume’s An Enquiry Concerning Human Understanding.

In programming inductive bias can be anything as simple as how many clusters to look for in a data set, to much more difficult issues like how to get a representative sample of images of a population for a face recognition system. (And just what is “representative” anyway?)

The Basel model I started with was trained on an even split of men and women but the majority of people in the training set were of european descent. This means that even though the model can be fitted to parameters representing other ethnicities it always has a slight in-built bias toward caucasian faces. With this in mind I then trained a new version of this program by fitting images from the FERET face recognition dataset (which is more representative of ethnicity composition in the states but still not perfect). I trained the system based on my own subjective interpretations and thus, like much of an artist’s work, the faces it produces are as much a reflection of me and my view of the world as they are any kind of objective scientific model. Then again, most academic researchers follow the same technique, utilizing the judgements of 5 men in an office instead of 1 woman in a studio.

I did all this work in matlab which I am by no means an expert in, and so I switched to Python for the rest of the code – mainly reading in various data files and turning that info into parameters for the matlab morphable model. The Biopython library proved valuable here!

And now I have a bit of an internal debate as to whether I should open source all this work or not. My impulse is to post the code online and let people do what they wish with it. But then another part of me wonders who will want to use it and what for? The point of the project is criticality and dialogue, not proving that this is technically possible. I never had the intention of making a “genetic portrait toolkit”. Do I really want to make this easier? Thoughts?