Agu, Emmanuel O.
The goal of this project was to extract key features from photographs of faces and use machine learning to classify subjects as either sober or drunk. To do this we analyzed photographs of 53 subjects after drinking wine and extracted key features which we used to classify drunkenness. We used random forest machine learning to achieve 81% accuracy. We built an android application that using our classifiers to estimate the subjects drunkenness from a selfie.
Worcester Polytechnic Institute
Major Qualifying Project
All authors have granted to WPI a nonexclusive royalty-free license to distribute copies of the work, subject to other agreements. Copyright is held by the author or authors, with all rights reserved, unless otherwise noted.