Active Hackathon

Computer Trained To Recognise ‘Healthiest’ Person, Can Accurately Predict BMI, Body Fat, Blood Pressure By Scanning A Face



Based on a study by author and Macquarie University psychology researcher Dr Ian Stephen, a computer model has now been trained to recognise a prospective “attractive” person.


Sign up for your weekly dose of what's up in emerging technology.

Attraction between two people may not just be the result of toned abs, the shape of the face, or curves. Dr Stephen’s finding add to the increasingly popular theory which suggests that modern-day attraction has less to do with personal taste and more to do with our biological instincts.

Based on Dr Stephen’s research, the computer model was programmed to recognise the “healthiest” face on the basis of the three major indicators of good health: body mass index (BMI), body fat percentage and blood pressure.

The computer was reportedly trained to recognise these three health indicators for 272 Asian, African and Caucasian faces. Once trained, the model was then able to accurately predict the BMI, body fat and blood pressure of any individual, just by analysing an image of their face.

“There’s always been this ‘beauty is in the eye of the beholder’ idea which essentially says that what we find attractive is just arbitrary and there is nothing inherent about an attractive person… Evolutionary theory has chipped in on that and essentially says that attractiveness is essentially a mechanism for recognising healthy, fertile, appropriate mates and also healthy friends and allies, because there’s obvious advantages to being friends with or mating with people who are healthy,” Dr Stephen said.

Dr Stephen was also part of a team who found that men who eat a diet rich in fruit and vegetables smell more attractive to women than those who eat high-carbohydrate or high-fat diets.

More Great AIM Stories

Prajakta Hebbar
Prajakta is a Writer/Editor/Social Media diva. Lover of all that is 'quaint', her favourite things include dogs, Starbucks, butter popcorn, Jane Austen novels and neo-noir films. She has previously worked for HuffPost, CNN IBN, The Indian Express and Bose.

Our Upcoming Events

Conference, in-person (Bangalore)
Machine Learning Developers Summit (MLDS) 2023
19-20th Jan, 2023

Conference, in-person (Bangalore)
Rising 2023 | Women in Tech Conference
16-17th Mar, 2023

Conference, in-person (Bangalore)
Data Engineering Summit (DES) 2023
27-28th Apr, 2023

Conference, in-person (Bangalore)
MachineCon 2023
23rd Jun, 2023

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM