Project # 143
FACIAL SYMMETRY QUANTIFICATION: LANDMARK-BASED ANALYSIS THROUGH COMPUTER VISION MODELING

Team Lead:	Anthony Gomez
Other Team Members:	Natalie Mar \| Katherine Zoller
Faculty Advisor(s):	Oguz Yetkin
Department:	BE
Project Type:	Senior Design
Title:	FACIAL SYMMETRY QUANTIFICATION: LANDMARK-BASED ANALYSIS THROUGH COMPUTER VISION MODELING
Abstract:	Facial drooping is one of the earliest signs in stroke patients and those at risk of stroke for the first time; however, it can be difficult to detect even the subtle changes. Landmark analysis through computer modeling can lead to insights into the possible severity or depth of asymmetry within our faces. Several different methods and equations for determining these parameters have been presented in previous studies and will be used for this study. This study aims to develop an asymmetry index (AsI) to establish a score range and to reduce subjectivity in neurological assessments, using a portable, self-contained system that quantifies facial asymmetry and droop via 3D facial landmark analysis. The accumulation of scores from the various quantification codes, with its consistency from previous methods would help in obtaining the normal population values that would then be used to provide a range in our AsI.
Poster:	View Poster #143 (PDF)
Judges Scoring:	Submit Evaluation (judges only)

Project # 143FACIAL SYMMETRY QUANTIFICATION: LANDMARK-BASED ANALYSIS THROUGH COMPUTER VISION MODELING