Skin Care via Artificial Intelligence Ankur Purwar PhD Principal - - PowerPoint PPT Presentation
Diagnostic and Personalized Skin Care via Artificial Intelligence Ankur Purwar PhD Principal Scientist, Procter & Gamble R&D, Singapore 10 research centers 65 OLAY has been creating 1,000 scientifically-advanced researchers Skin
Ankur Purwar PhD
Principal Scientist, Procter & Gamble R&D, Singapore
OLAY has been creating scientifically-advanced Skin Care for
research centers
researchers
consumers every year
Over
Million
Only 67% of women were able to find what they were looking for when browsing the facial Skin Care aisle
14% of women say they don’t know what their specific Skin Care needs are1
Don’t know
1P&G data on file
Your Personalized Skin Care regimen in a snap
Empowering skincare now and in the future
PROOF
Discoveries leading to OLAY Skin Advisor
DISCOVERY
Personalized Skin Care in a snap
DIAGNOSTICS
Discoveries Leading to OLAY Skin Advisor
Imaging Breakthroughs MDE and MES Studies Facial Mapping Study VizID ™ Learning Algorithm Platforms
Beauty Imaging System Chromophore mapping and SIAScopy VISIA ™ technology OLAY Skin Advisor Imaging for R&D OLÉ ™ (Overhead Lighting Environment)
African
Caucasian
Real (Chronological) Age Perceived Age Identification of “Exceptional
Agers”.
Prof Alexa Kimball
Actual Age 44 years Perceived: 57 years Perceived: 29 years
Characterisation of the facial skin of the world’s women. Canfield VECTRA Full-face 3D capture
Original Image Shape corrected to average Topography corrected to average Colour corrected to average
Understanding the differential characteristics and ageing of skin in five zones across the face.
Forehead Cheek Chin Crow’s Feet Under Eye
Flagler, M et al., New biological insights into skin ageing around the eye. Presented at the 74th Annual Meeting of the American Academy of Dermatology, Washington D.C., 2016
VizID™ Learning Algorithm Platforms
Predicted Age Feature Detection Age Prediction
▪ Trained a deep learning model with 50,000 facial images ▪ Model is able to further detect a person’s key aging areas and determine how old they actually look.
Visible Skin Age Prediction
Weitz, S et al., Improving Consumer Compliance Through Better Product Recommendation- New Skin Advisor Tool. Presented at the 75th Annual Meeting of the American Academy of Dermatology, 2017
Visage (model sees same person 8 times) Dermatologist (8 different derms see same person 1 time) Image Age Range N=625 people N=4977 total derm grades Derm Range= 20.27 years Visage Range= 2.88 years
Technical Validation of Skin Age Model
More precise than dermatologist’s at predicting visible age
It Starts with a Scientific ‘Selfie’
Step 1 Image Acquisition Step 3 Questionnaire Step 2 Skin Analysis
Step 4 Product Recommendation
Step 4 Regimen Reco
Computed “Skin Age”. “Best” and “Improvement Needed” areas identified.
Regimen recommendation augmented by a “Synaptic Intelligence” platform from Nara Logics, Inc.
Key results metrics post- 4 weeks product use indicate satisfaction with the skin advisor product recommendation and improved consumer compliance. Key results metrics pre-product use indicate satisfaction with the skin advisor product recommendation
Weitz, S et al., Improving Consumer Compliance Through Better Product Recommendation- New Skin Advisor Tool. Presented at the 75th Annual Meeting of the American Academy of Dermatology, 2017
1. 100 US women, age 25-65, facial moisturizer users, were enrolled in a 4-week online consumer test. 2. Group 1 (n=50) received a product regimen based on the skin advisor deep learning algorithm and preferences and Group 2 (n=50) self-selected a product regimen. 3. Self-assessment questions were completed pre-use and post- 4 weeks product use.
System upgrades Pioneering new “smart” technology Smarter with every use…
Your Personalized Skin Care regimen in a snap