November 27, 2018
-
The AI that can tell how old people REALLY are from a photograph
Researchers have unveiled a new AI system that can predict how old you are simply by looking at a photo of part of your face. And, in what may not come as much of a surprise to many, the experts say the corners of your eyes are the biggest giveaway. The new technique tested on more than 8,000 photos could pave the way for more precise age estimations even when just a small portion of the face is visible, and lead to more personalized skin care treatments.
In a new study, researchers from AI skin care firm Haut.AI used 8,414 anonymized high-resolution images to test the accuracy of their system. They found the skin near the corners of the eye, and the general eyelid area, were the most effective in predicting age. This type of information can be used to evaluate different factors that affect aging, including lifestyle, medical, and cosmetic interventions.
Anastasia Anastasia Georgievskaya, CEO of Haut AI, said: ‘The future of consumer business is in personalization and I hope that this study will lay the foundation for AI-powered consumer skincare and healthcare. Understanding the many biological processes in skin using AI may lead to the many breakthroughs down the road.’
The system was able to predict the correct age with 2.3 years Mean Absolute Error (MAE).
According to the researchers, the work is a step toward AI-driven ‘aging clocks’ that could measure every step of the aging process. This could play out in a number of formats, including smart sensors in clothing and other wearables, they say.
Alex Zhavoronkov, PhD, CEO of Insilico Medicine, said: ‘Deep neural networks (DNNs) are often perceived as the black boxes, however, this is a common misconception. Aging research helps make DNNs more interpretable. This study shows what area of the face is most important for age estimation but when you do it on other data types like gene or protein expression, it is possible to see what genes are more important and construct the casual networks. I personally believe that the AI aging clocks are among the most important breakthroughs in longevity biotechnology and we will see the many advances resulting from similar studies. As for this study, you may want to take care of the eye corners if you want to look younger to some of the age predictors.’
Extracted from: www.dailymail.co.uk