Perso: Tale-to-scale skincare and makeup tech device, the future of Beauty Technology.
Personalized and on-demand at-home devices are the big upcoming trend in the beauty technology industry. Nowadays we talk about “ Beauty Tech”. These types of devices were the stars at the Consumer Electronics Show this year. These new digital products use AR or AI
AR stands for « augmented reality », which is basically the action of enhancing your reality with more information.
It allows an interactive experience in a real-world environment where the objects or humans that reside in, are enhanced by computer-generated perceptual information, across multiple sensories. It is a system that fulfills three basic features: a combination of real and virtual worlds, real-time interaction, and accurate 3D registration of virtual and real objects.
In other words, it uses technology to overlay digital information on an image of something being viewed through a device, a smartphone camera for example. AR can display a data overlay that shows directions or the time, to holograms floating in the middle of a room.
AI stands for artificial intelligence. It is the capability of a machine to imitate intelligent human behaviors.
AI is often broken into two groups: applied and general. Applied AI refers to “smart” systems that address a specific need, like trading stocks or personalizing ads. General AI, encompasses systems or devices which can do any task that a human being can. For example, think about Westworld and other sci-fI movies.
But, what is Perso?
Well, personalization is the future of beauty technology.
Perso is a smart device that creates tale-to-scale, on-demand formulas for lipstick, foundation, and skincare. All this from your bathroom counter, for only, $ 300 ! It is launching this year by L’Oreal.
Which technology is used?
First thing first! What is an algorithm ?! An algorithm, in mathematics and computer science, is a finite sequence of computer-implementable instructions. It is generated to solve a class of problems or to perform any type of calculation that includes both arithmetical and non-arithmetical steps and which follows a well-defined model.
Well here is an example …. 1 +1 = 2, is an algorithm ….Still not convinced? Here is a cool explanation from David J.Malan.
So, which problem does L’Oreal solve with its algorithm ?
Perso technology used an Artificial Intelligence-powered algorithm developed by ModiFace with L’Oréal’s skin aging expertise and their photo database. It uses deep learning, also known as deep structured learning which is part of a broader family of machine learning methods (or when algorithms improve automatically through experience and by the use of data).
It is based on neural networks ( which are computing systems kind of inspired by our biological neural system) with representation, which finally is seen as a part of artificial intelligence. Machine learning algorithms build models based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so.
So Modiface alongside L’Oreal’s Technology Incubator created an algorithm that has been trained on 6000 clinical images from L’Oréal’s R&I evaluation and knowledge studies. These studies have been conducted with Skin Aging Atlases, and then a new model has been created on over 4500 smartphone selfies for 3 groups of women from multiple ethnicities, in 4 different lighting conditions. Perso has a high level of skin assessment precision. Accurate results were obtained with different facial expressions and photo-taking conditions (light, phone position) similar to those used by consumers.
L’Oréal’s Skin Aging Atlases are the first exhaustive atlases of facial aging, addressing visual aging signs. Studies for Skin Aging Atlases were carried out in France, China, Japan, India, and the United States on a total of 4000 women and men aged from 20 to 80 years. Skin Atlases allow to evaluate or predict the general aging of the face and are used today for a clinic.
How does it work?
Perso has its mobile application. So you take a selfie or upload a portrait to the brand website. Then you enter your personal skincare concerns into the Perso app. The technology detects several concerns. Using Breezometer geo-location data, Perso takes into account the local environmental conditions that can influence the state of your skin. These might include weather, temperature, pollen, UV index, and humidity.
All of this data helps to create a personalized blend of skincare, dispensed in a rightly portioned, single dose at the top of the device for a clean application. The technology adjusts for morning and evening.
How did L’Oreal achieve this?
“With the acquisition of ModiFace, we have started the second phase of L’Oréal’s digital transformation focused on reinventing the beauty experience through technologies such as AR and AI.” Jean-Paul Agon, L’Oreal Chairman and CEO.
What the acquisition of Modiface means for L’Oréal ?
Basically, L’Oreal offered itself an augmented reality and artificial intelligence entity. ModiFace powers a number of websites focused on facial visualization and virtual modification. ModiFace’s story starts in 1999 at Stanford University, where Parham Aarabi initiated research on automatic face analysis. His work continued at the University of Toronto, where he worked on face processing algorithms (work which later won a world-wide innovation prize from MIT). In 2006, ModiFace Inc. was born.
Today, ModiFace is the world’s largest and most advanced virtual makeover platform. They had a hand in the creation of many customs augmented reality beauty apps, including those from Sephora and Estée Lauder. This acquisition gives L’Oréal major advantages over its competitors who will now find new business partners to stay ahead in the AR beauty market competition.
At the same time I am not sad for them, cause again, the next algorithm might solve this problem.
Source: WGSN, Wikipedia, Cosmetic Design Europe, L’Oreal, Allure, The Verge, L’Oreal Incubator, David J.Malan, Siecle Digital France, It is nice that, Pinterest
