Rana el Kaliouby: This app knows how you feel -- from the look on your face
Rana el Kaliouby - Computer scientist
What if a computer could recognize your facial expression, and react to how you feel? Rana el Kaliouby sees big possibilities in making technology emotionally aware. Full bio
every aspect of our lives,
to how we do business and make decisions,
how we connect with one another.
in a world like this,
more and more of our lives like this --
from my daughter last night --
back into our digital experiences.
a Ph.D. program at Cambridge University.
who had to stay in Egypt,
away from home,
more hours with my laptop
had absolutely no idea how I was feeling.
online with my family back home,
disappeared in cyberspace.
and on some days I was actually crying,
these emotions was this.
has lots of I.Q., but no E.Q.;
but no emotional intelligence.
could sense our emotions?
how we felt and reacted accordingly,
intelligent friend would?
and respond to our emotions,
one of the most powerful channels
social and emotional states,
facial muscle movement an action unit.
which is the main component of a smile.
some smiles going on.
It's the brow furrow.
these textures and wrinkles.
a strong indicator of a negative emotion.
hundreds of emotions.
these facial emotions is hard,
they can be fast, they're subtle,
the smile and the smirk.
but they mean very different things.
can make you become famous.
for a computer to be able
between the two expressions.
of people we know to be smiling,
textures and wrinkles
have common characteristics,
characteristics of a smile,
This is a smile expression."
how this technology works
preferably somebody with a face.
from being a research project at MIT
to make this technology work,
the core emotion engine
with a camera, like this iPad.
has essentially found Cloe's face,
feature points on her face,
her mouth and her nose.
can it recognize her expression?
Yep, awesome. (Laughter)
this is a genuine smile, it's great.
go up as she smiles.
to see if the computer can recognize?
to make that happen.
indicator of surprise.
an indicator of confusion.
action units. There's many more of them.
an emotion data point,
to portray different emotions.
look like you're happy.
when Zayn left One Direction.
negative, so you must have been a big fan.
or negative an experience is,
expressive she is as well.
to this real-time emotion stream,
with anybody she wanted to.
12 billion of these emotion data points.
database in the world.
from 2.9 million face videos,
to share their emotions with us,
as personal as our emotions,
that you might suspect.
their smiles last longer,
what it is that men and women
more expressive than men,
in the U.K. between men and women.
than younger people.
than men the same age,
the most about this data
to be expressive all the time,
in front of our devices alone,
cat videos on Facebook.
texting, shopping online,
and voting behavior;
or emotion-enabling technology,
that are especially close to my heart.
can help individuals
read the faces of others,
on the autism spectrum interpret emotion,
if your learning apps
would in a classroom.
knows that you're stressed,
from binge eating. (Laughter)
back home in a very natural way,
in the same room together?
to have an emotion chip,
when we couldn't just frown at our device
you didn't like that, did you?"
so many applications of this technology,
build them all ourselves,
so that other developers
there are potential risks
many years doing this,
part of the conversation.
about this technology,
in how it's being used.
of our lives become digital,
trying to curb our usage of devices
is to bring emotions into our technology
that have separated us
we have this golden opportunity
connect with machines,
About the speaker:Rana el Kaliouby - Computer scientist
What if a computer could recognize your facial expression, and react to how you feel? Rana el Kaliouby sees big possibilities in making technology emotionally aware.
Why you should listen
Rana el Kaliouby, chief science officer and co-founder of Affectiva, an MIT Media Lab spin-off, is on a mission to bring emotion intelligence to our digital experiences. She leads the company's emotion analytics team, which is responsible for developing emotion-sensing algorithms and mining the world's largest emotion data database. So far, they've collected 12 billion emotion data points from 2.9 million face videos from volunteers in 75 countries. The company’s platform is used by many Fortune Global 100 companies to measure consumer engagement, and is pioneering emotion-enabled digital apps for enterprise, entertainment, video communication and online education.
Entrepreneur magazine called el Kaliouby one of “The 7 Most Powerful Women To Watch in 2014,” and the MIT Technology Review included her in their list of the “Top 35 Innovators Under 35.”
Rana el Kaliouby | Speaker | TED.com