Master Thesis Defense: Amir Zafar Asoodeh
Speaker: Amir Zafar Asoodeh
Supervisor: Dr. T Popa
Examining Committee: Drs. S. P. Mudur, C. Y. Suen, E. Shihab (Chair)
Title: Face and Frame Classification Using Geometric Features for a Data-driven Eyeglass Recommendation System
Date: Monday, January 19, 2015
Time: 11:30 a.m.
Place: EV 3.309
Recommending glasses based on face and frame features is the main issue of this thesis. In this work we present an automatic classification method for face and eyeglass types that we incorporated in a data-driven eyeglass recommendation system. Using a supervised learning technique, we identified the geometric discriminatory features that can be used to classify both the face type and the eyeglass type form a single photograph. Our classification method reaches near 100% accuracy. We ran this classification on over 200 photographs and we surveyed 100 people on the compatibility between face and eyeglasses. Using this data we created an eyeglass recommendation system that we have validated experimentally.