Face It

Pallab Paul

Unknown

9 0

A mobile application that detects a person's facial structure as well as information about current trends to recommend a person hairstyles. ...learn more

Project status: Published/In Market

Mobile, RealSense™, HPC, Artificial Intelligence

Intel Technologies
Intel Opt ML/DL Framework, Intel CPU

Links [2]

Overview / Usage

Face It is a mobile application that uses computer vision to acquire data about a person’s facial structure as well as periodic inputs by hair stylists to accumulate data about regional fashion trends. The application then utilizes artificially intelligent software to recommend trendy haircuts and beard styles that complement each individual's facial structure. The application will allow users to test out different looks with filters that are generated based on the recommendations provided. Face It also generates product recommendations that will be based on responses to questions that each user will input during the registration process about their hair, skin, and lifestyle. Face It ensures that every haircut a man gets makes him look his best. Face It also solves the product selection dilemma that a man experiences.

Methodology / Approach

We trained a convolution neural network to make this project function. We used Google's Inception v3 model as the architecture to mimic because of it's large popularity and because of it's amazing results during the ImageNet Large Scale Visual Recognition Competition. We continued to improve and train our model with more specific data sets until we had above 80% accuracy.