Welcome to the First International Beauty Contest Judged by
Artificial Intelligence
Winners of Beauty.AI 2.0 contest
Partners and Supporters
Robot Jury
RYNKL
Wrinkle Detector
MADIS
Model Alliance Digital Intelligence Scout
Symmetry
Master
AntiAgeist
This time the robot jury consisted of the 5 main robots:
RYNKL, which scored people by the "wrinkleness" within their age group;
PIMPL, analysing the amount of pimples and pigmentation;
MADIS, which scored people by their similarity to models within their racial group;
Symmetry Master evaluating the symmetry of the face;
AntiAgeist, a robot estimating the difference between the chronological and perceived age.

RYNKL and PIMPL algorithms show the amount of wrinkles and pimples, respectively (the less is the better). AntiAgeist shows the delta of chronological and perceived age (the less the score - the younger you look).
Symmetry Master shows the rate of nonsymmetry (the less is more symmetric)
MADIS score shows the similarity to models and actors within your age and ethnic group (50 to 100).
PIMPL
Science behind this
What matters in beauty is perception. Perception is how you and other people see you, and this perception is almost always biased. Still, healthy people look more attractive despite their age and nationality.

This has enabled the Youth laboratories team of biogerontologists and data scientists, who believe that in the near future machines will be able to get a lot of vital medical information about people's health by just processing their photos, to develop a set of algorithms that can accurately evaluate the criteria linked to perception of human beauty and health where it is most important – the human face. But evaluating beauty and health is not enough. The team's challenge is to find effective ways to slow down ageing and help people look healthy and beautiful.

There were many attempts to do this in the past, but this time it will have a global impact because of the advances in deep learning, symbolic learning and massive semantic analysis.
Leaderboard
Select age group
Contest winners and Robot Jury teams will be offered cosmetics prizes.


And both Human Winners and Robot Jury will go down to history as the first on the Earth, who took part in The First International Beauty Contest Judged by Artificial Intelligence.

More about Beauty.AI 1.0 and Beauty.AI 2.0

Age group 18—29
Age: 18
Real age prediction: 13
Perceived age prediction: 15
AntiAgeist score: 2
PIMPL score: 1,3
RYNKL score: 1
MADIS score: 97
Symmetry Master score: 5,2
Women
Lu Sophia
Age: 27
Real age prediction: 23
Perceived age prediction: 23
AntiAgeist Score: 7
PIMPL score: 1,2
RYNKL score: 3
MADIS score: 96
Symmetry Master score: 3,1
Margeri Ottis
Age: 26
Real age prediction: 18
Perceived age prediction: 16
AntiAgeist score: 9,5
PIMPL score: 1,2
RYNKL score: 5
MADIS score: 96
Symmetry Master Score: 14,0
Kerri Kinney
Age: 25
Real age prediction: 18
Perceived age prediction: 20
AntiAgeist score: 6,5
PIMPL score: 1,1
RYNKL score: 2
MADIS score: 96
Symmetry Master score: 1,3
Margarita Shestakova
Age: 29
Real age prediction: 23
Perceived age prediction: 23
AntiAgeist score: 9
PIMPL score: 1,2
RYNKL score: 3
MADIS score: 97
Symmetry Master score: 5,2
Evgeniya Miruk
Age group 18—29
Age: 20
Real age prediction: 18
Perceived age prediction: 17
AntiAgeist score: 3
PIMPL score: 1,4
RYNKL score: 4
MADIS score: 95
Symmetry Master score: 3,1
Men
Boyd Dijkstra
Age: 21
Real age prediction: 21
Perceived age prediction: 22
AntiAgeist score: 1,5
PIMPL score: 1,9
RYNKL score: 6
MADIS score: 94
Symmetry Master score: 3,1
John Schutts
Age: 25
Real age prediction: 18
Perceived age prediction: 17
AntiAgeist score: 8
PIMPL score: 3,1
RYNKL score: 1
MADIS score: 97
Symmetry Master score: 5,2
Tom Lee
Age: 25
Real age prediction: 23
Perceived age prediction: 20 AntiAgeist score: 6,5
PIMPL score: 2,2
RYNKL score: 4
MADIS score: 92
Symmetry Master score: 7,6
Sebastian Niedermeier
Age: 27
Real age prediction: 24
Perceived age prediction: 18
AntiAgeist score: 9,5
PIMPL score: 1,2
RYNKL score: 3
MADIS score: 96
Symmetry Master score: 0,9
Dmitriy Berdnikov
Age group 30—39
Age: 31
Real age prediction: 18
Perceived age prediction: 16
AntiAgeist score: 14,5
PIMPL score: 0,8
RYNKL score: 3
MADIS: 96
Symmetry Master score: 3,1
Women
Pınar Acar Övet
Age: 39
Real age prediction: 32 Perceived age prediction: 25
AntiAgeist score: 18
PIMPL score: 1
RYNKL score: 3
MADIS: 92
Symmetry Master score: 2,4
Age: 35
Real age prediction: 39
Perceived age prediction: 33
AntiAgeist score: 10
PIMPL score: 1,6
RYNKL score: 6
MADIS: 96
Symmetry Master score: 3,7
Vera Belova
Age: 30
Real age prediction: 23
Perceived age prediction: 23 AntiAgeist score: 10
PIMPL score: 1,9
RYNKL score: 3
MADIS score: 89
Symmetry Master score: 1,1
Milana Dzhidzhoeva
Age: 30
Real age prediction: 13
Perceived age prediction: 16
AntiAgeist score: 13,5
PIMPL score: 0,6
RYNKL score: 2
MADIS score: 94
Symmetry Master score: 3,1
Heidi Wang
Shannon Wallace Powers
Age group 30—39
Age: 32
Real age prediction: 13
Perceived age prediction: 16
AntiAgeist score: 25
PIMPL score: 1,5
RYNKL score: 4
MADIS score: 96
Symmetry Master score: 7
Men
Toru Igami
Age: 39
Real age prediction: 46 Perceived age prediction: 41
AntiAgeist score: 10
PIMPL score: 2,7
RYNKL score: 7
MADIS score: 91
Symmetry Master score: 1,0
Age: 31
Real age prediction: 19
Perceived age prediction: 17
AntiAgeist score: 14
PIMPL score: 1,6
RYNKL score: 3
MADIS: 99
Symmetry Master score: 1,1
Dmitry Ermolaev
Age: 32
Real age prediction: 34
Perceived age prediction: 29 AntiAgeist score: 9
PIMPL score: 1,9
RYNKL score: 4
MADIS: 90
Symmetry Master score: 13,1
Johan Wallquist
Age: 31
Real age prediction: 24
Perceived age prediction: 17
AntiAgeist score: 14
PIMPL score: 2,2
RYNKL score: 6
MADIS: 98
Symmetry Master score: 1,4
Asan Sultanov
Leonid Bugaev
Age group 40—49
Age: 42
Real age prediction: 39
Perceived age prediction: 27
AntiAgeist score: 20
PIMPL score: 1,8
RYNKL score: 3
MADIS score: 96
Symmetry Master score: 1,3
Women
Fima Ro
Age: 42
Real age prediction: 13
Perceived age prediction: 16
AntiAgeist score: 25,5
PIMPL score: 1,4
RYNKL score: 3
MADIS score: 98
Symmetry Master score: 1,4
Dang Moo
Age: 41
Real age prediction: 32
Perceived age prediction: 25
AntiAgeist score: 20
PIMPL score: 0,8
RYNKL score: 3
MADIS score: 91
Symmetry Master score: 2,7
Michele Daugherty
Age: 40
Real age prediction: 25
Perceived age prediction: 23 AntiAgeist score: 20
PIMPL score: 0,8
RYNKL score: 4
MADIS score: 97
Symmetry Master score: 1,3
Sofia Lania
Age: 46
Real age prediction: 32
Perceived age prediction: 27
AntiAgeist score: 24
PIMPL score: 1,8
RYNKL score: 2
MADIS score: 92
Symmetry Master score: 6,3
Sheri Eastman
Age group 40—49
Age: 49
Real age prediction: 43
Perceived age prediction: 42
AntiAgeist score: 19,5
PIMPL score: 1,4
RYNKL score: 6
MADIS score: 90
Symmetry Master score: 14,0
Men
A Hajdu
Age: 40
Real age prediction: 39 Perceived age prediction: 35 AntiAgeist score: 14
PIMPL score: 0,8
RYNKL score: 3
MADIS score: 96
Symmetry Master score: 2,0
Dmitry Vatyutov
Age: 47
Real age prediction: 35
Perceived age prediction: 33 AntiAgeist score: 22
PIMPL score: 1,7 2 94
RYNKL score: 2 94
MADIS score: 94
Symmetry Master score: 3,1
Gaedeke Architekten
Age: 41
Real age prediction: 32
Perceived age prediction: 33
AntiAgeist score: 16
PIMPL score: 1,9
RYNKL score: 2
MADIS score: 88
Symmetry Master score: 1,1
Sergey Gudyrin
Age group 50—59
Age: 54
Real age prediction: 44
Perceived age prediction: 16
AntiAgeist score: 37,5
PIMPL score: 1,2
RYNKL score: 2
MADIS score: 99
Symmetry Master score: 2,3
Women
NY Yoon
Age: 56
Real age prediction: 59
Perceived age prediction: 25
AntiAgeist score: 35
PIMPL score: 1,9
RYNKL score: 6
MADIS score: 99
Symmetry Master score: 1,3
Nataliya Karpova
Age: 52
Real age prediction: 40
Perceived age prediction: 25
AntiAgeist score: 31
PIMPL score: 2,7
RYNKL score: 2
MADIS score: 94
Symmetry Master score: 3,1
Yukako Asano
Age: 57
Real age prediction: 39
Perceived age prediction: 33 AntiAgeist score: 32
PIMPL score: 1,1
RYNKL score: 3
MADIS score: 93
Symmetry Master score: 5,7
Elena Mashkova
Age: 51
Real age prediction: 44
Perceived age prediction: 37
AntiAgeist score: 24
PIMPL score: 1,1
RYNKL score: 3
MADIS score: 98
Symmetry Master score: 1,4
Maggie B
Age group 50—59
Age: 52
Real age prediction: 43
Perceived age prediction: 33
AntiAgeist score: 27
PIMPL score: 2,1
RYNKL score: 1
MADIS score: 90
Symmetry Master score: 2,7
Men
Alan Jope
Age: 50
Real age prediction: 53 Perceived age prediction: 14 AntiAgeist score: 34,5
PIMPL score: 2,8
RYNKL score: 3
MADIS score: 96
Symmetry Master score: 3,1
Raul Lopez
Age: 51
Real age prediction: 43
Perceived age prediction: 37
AntiAgeist score: 24
PIMPL score: 1,9
RYNKL score: 5
MADIS score: 95
Symmetry Master score: 1,1
Henrik Brix
Age: 58
Real age prediction: 48
Perceived age prediction: 52 AntiAgeist score: 23,5
PIMPL score: 0,6
RYNKL score: 3
MADIS score: 90
Symmetry Master score: 13,1
Nikolay Ostarkov
Age group 60—69+
Age: 69
Real age prediction: 67
Perceived age prediction: 57
AntiAgeist score: 32
PIMPL score: 1,1
RYNKL score: 7
MADIS score: 94
Symmetry Master score: 5,5
Women
Lavana
Age: 70
Real age prediction: 60
Perceived age prediction: 52
AntiAgeist score: 35,5
PIMPL score: 0,6
RYNKL score: 2 92 11,5
MADIS score: 92
Symmetry Master score: 11,5
Maria Rita Resende
Age: 70
Real age prediction: 67
Perceived age prediction: 63
AntiAgeist score: 30
PIMPL score: 1,3
RYNKL score: 5
MADIS score: 94
Symmetry Master score: 3,1
Galina Koposova
Age group 60—69+
Age: 74
Real age prediction: 58
Perceived age prediction: 52
AntiAgeist score: 39,5
PIMPL score: 0,8
RYNKL score: 5
MADIS score: 87
Symmetry Master score: 2,7
Men
Vitali Dunin
Age: 66
Real age prediction: 48
Perceived age prediction: 44
AntiAgeist score: 35,5
PIMPL score: 1,1
RYNKL score: 2
MADIS score: 93
Symmetry Master score: 14,5
Ark Prokop
Age: 60
Real age prediction: 48
Perceived age prediction: 46
AntiAgeist score: 28,5
PIMPL score: 5,9
RYNKL score: 2
MADIS score: 95
Symmetry Master score: 6,2
Anber Beran
Beauty.AI 2.0 contest completed
More about Beauty.AI 2.0 results
The second beauty contest, where humans are judged by the robots completes with over six thousand images evaluated by the five robot judges. In addition to the panel of judges from the first contest, Beauty.AI 2.0 featured three new robot judges including:
  • "Average Face" built on the hypothesis that the closer the face is to the average face within the ethnic group, the more attractive it is
  • "AntiAgeist" evaluating the difference between the predicted and actual chronological age
  • "PIMPL" evaluating the number and distribution of pimples and other dark spots (but not freckles)

The results were sent to the individual participants via secure link and winners were announced at http://winners2.beauty.ai/#win .

The results were surprising, since the consensus scores provided by the robot jury disagreed with human opinion. Tens of participants responded with angry emails criticizing the winners selected by the robot jury.

Statements including "what is your "robot" worth??? One walk through a shopping-mall and I will discover more attractive people vs. that ones "won" your Beauty Contest", "If this is how I will be judged in the future, I don't want to see it", "You need human opinion" were among the most pleasant ones with rare positive comments including "this contest is a confidence booster!".

"We were shocked by the outrage caused by the leaderboard. Many participants disagreed with the jury and proposed getting a human opinion. But with every Beauty.AI contest we are getting more ideas on how to evaluate the human face and even go beyond the face evaluating multiple features of the human body and even social profiles", said Anastasya Georgievskaya, Research Manager at Youth Laboratories, the co-organizer of Beauty.AI.

The team received proposal to turn the Beauty.AI into a physical on-stage show with robots judging human models and may consider launching a pilot in 2017. It also received several proposals to run Bauty.AI contests on a regional basis. In September 2016 Youth Laboratories will launch Miss. Moscow State University contest using a novel panel of robot judges and series of hackathons for algorithm developers.

The Beauty.AI 3.0 will launch on October 1st and algorithm developers with novel concepts evaluating perception of the human face are welcome to participate.

"With every contest we are getting new ideas, new partners and new robots. I think that in 2-3 years these technologies will be very important and will help facilitate human-robot interaction. We are also finalizing the new app to track health status using your mobile phone", said Konstantin Kiselev, Director of Development at Youth Laboratories.

About Beauty.AI

Beauty.AI is the first beauty contest judged entirely by robot jury, where humans and robots can apply to participate. Every quarter this platform will open submissions for multiple developers of beauty-ranking algorithms to train and test their systems.

The project was launched by Youth Laboratories team, whose aspiration is to grasp the fundamentals of human nature and effective ways of aging slow down and retaining the youthful look for as long as possible.

About Youth Laboratories

Youth Laboratories is a company dedicated to helping people retain youthful state for as long as possible using advances in machine vision and artificial intelligence. The company is run by a team of computer and data scientists, biologists, biogerontologists and business people on a quest to develop novel biomarkers and anti-aging interventions. The company develops series of mobile applications that track age-related changes, wrinkles, pimples, dark spots and other parameters affecting perception of beauty, health and youthfulness and help evaluate the effectiveness of multiple interventions.

Beauty.AI in GooglePlay: https://play.google.com/store/apps/details?id=com.beauty_ai
Beauty.AI in App Store:https://itunes.apple.com/ru/app/beauty.ai/id1060865109?mt=8
Beauty.AI web-site: http://beauty.ai
Beauty.AI on FB: https://www.facebook.com/aibeautycontest/
Beauty.AI on Twitter: https://twitter.com/aibeautycontest

Contact the team: team@beauty.ai

Thank you for participating in Beauty.AI 2.0!
Join Beauty.AI 3.0
Be the First Beauty Queen or King Judged by Robots
Made on
Tilda