Shonan Beauty Clinic (SBC)
A big beauty clinic with 85 locations in Japan and oversea branches. They offer a full service of regenerative and rejuvenation medispa plus plastic surgeries by world-renowned cosmetic surgeons.
The Business’s Needs
- Decision of taking either rejuvenation treatment or eye double-fold surgery or not basing on doctor’s experience barely is not persuasive and contains risks for patients.
- Experienced doctors in Aesthetics Surgery are expensive and in shortage (especially in aging countries like Japan).
- Promised to bring “state of the art services” with ”top of the line equipment”, SBC needs a powerful Aesthetic Surgery Recommendation System to help customers and surgeons make right decisions easier.
- In this project, we proposed a deep learning-based recommendation system for the 2 popular aesthetic surgeries – rejuvenation treatment and eye double-fold surgery just basing on the original eye photos of the patients.
- The deep learning model built based on the dataset of before- and after-surgery facial images can estimate the probability of the perfection of some parts of a face.
We preliminarily achieve 88.9 and 93.1% accuracy on rejuvenation treatment and eye double-fold surgery, respectively.
AI (Deep learning)
Firstly, a convolutional auto-encoder is trained by eye images before and after surgery captured from various angles. The trained encoder is utilized to extract learned generic eye features.
Secondly, the encoder is further trained by pairs of image samples, captured before and after surgery, to predict perfection score. Based on this score, the system would suggest whether some sorts of specific aesthetic surgeries should be performed.
Flowchart of the method