What does your face reveal about you?

Facial recognition systems are typically used to identify or verify a person for security purposes. Now, researchers at the University of North Carolina Wilmington are using facial recognition technology as a diagnostic tool to determine health risks.

TRANSCRIPT

Facial-recognition systems are typically used to identify or verify a person for security purposes.

Now researchers at the University of North Carolina Wilmington are using facial-recognition technology as a diagnostic tool to determine health risks.

Here's the story.

And I get into the points?

Yeah, those are actual units, like I was talking about, the facial muscles.

Okay.

Yeah.

This is a story about faces.

Well, not just my face.

So, think about a place with lots of people... say the North Carolina State Fair.

All those people, all those faces, young and old, happy and sad, and every age and expression in between.

And all those faces tell a story about that individual.

So, when we look at a face, you know, and we're trying to identify that face, again, we say, male or female, right?

Then we say roughly an age.

And then we say roughly a race.

And then we say, 'Oh, okay.

Do I know anybody who looks like these things -- this age, this gender, and this race?'

And then we start searching in our database, our brain database, of faces like that.

That's how we pick out faces in a crowd.

It's called facial recognition.

And that prompted Dr. Karl Ricanek to wonder whether a computer could do the same thing and perhaps much more.

So, we started out looking and modeling the face.

And then we discovered that, 'Wow.

There's all this other information that I can extract from a face that has nothing to do with identity.' But if you pair it with identity, wow, we improve face recognition tremendously.

That's called facial analytics.

Researchers at the Institute for Interdisciplinary Studies in Identity Science at the University of North Carolina Wilmington have studied the face for 12 years.

They've discovered that unhealthy habits, over time, as well as certain chronic conditions leave their markers on the face.

In short, understand the factors affecting health, you'll find and understand the changes on the face.

Researchers mapped 250 landmark points on the face, and they've developed software so computers can create feature maps and analyze the findings, comparing a test subject's face to others in their category.

Take smoking.

So, if you are a long-time smoker, for example, you start to affect the face in very specific ways.

You start to develop wrinkles in certain areas of the face.

And if you think about sort of the biology of smoking, then it makes sense, because what smoking does is -- it literally dries out the dermis layer, right?

And so what happens is -- then you start to prematurely wrinkle in certain areas.

And here's another example.

Let's go back to my face.

I wanted to test the software to see if it could capture and understand something really basic -- my expressions.

...when you have a different expression.

So, for example, if you have joy, there are a set of muscles which get engaged.

And then so what you will see here is -- it will just give you whether, you know, you have sadness or surprise or you just have a neutral expression or you have fear or disgust.

So, the box that you're looking at there is a face detection.

Right here.

Yes.

Okay.

And it looks like it's highlighting certain areas.

Yes.

And those are the landmarks.

So, after the face detection is done, it will look for your eye, it will look for your nose tip, and it will look for your mouth.

So, basically, it's registering your face.

So, the box is the first thing.

So it detects the face, and inside the box, it will look for different landmarks, basically, the different features in your face.

Because certain parts of my face register joy or disgust.

Correct.

So, and those points, those red points, are used to detect different action units on your face.

Okay.

All right.

So, let me get -- So, smile.

[ Laughs ] Watch the charts.

Joy registered strongly.

And the computer interpreted my lost smile as sadness.

Researchers have found a person's facial features change as their health changes.

For example, weight loss can be spotted.

So, the new focus is whether the face can be used as a healthcare tool and whether it can predict life expectancy.

I see nothing but how we can help humanity with this technology.

So, just think about it.

I mean, if we can use the face and other technologies to integrate together to come up with -- let's call it a health index that we can provide to anyone.

And all they need is a smartphone that can take a selfie, and they can start to understand what their health index is.

And they can use this health index to make changes in their life.

So, if your health index is bad, you can make those changes.

So, the beauty of the face -- I mean, it has a lot of information.

And I'm hoping that we can use that information for good.