A Talk by a YSU Graduate on Automatic Macro‐ and Micro‐ Facial Expression Spotting and Applications
Abstract: Automatically determining the temporal characteristics of facial expressions has extensive application domains such as human-machine interfaces for emotion recognition, face identification, as well as medical analysis. However, many papers in the literature have not addressed the step of determining when such expressions occur. This talk will address the problem of automatically segmenting macro- and micro-expressions frames (or retrieving the expression intervals) in video sequences, without the need for training a model on a specific subset of such expressions. The proposed method exploits the non-rigid facial motion that occurs during facial expressions by modeling the strain observed during the elastic deformation of facial skin tissue. The method is capable of spotting both macro expressions which are typically associated with emotions such as happiness, sadness, anger, disgust, and surprise, and rapid micro- expressions which are typically, but not always, associated with semi-suppressed macro-expressions. Additionally, the method has been used to automatically retrieve strain maps generated from apex of expressions for human identification. A novel 3-D surface strain estimation algorithm using commodity 3-D sensors aligned with an HD camera will also be presented.
Matthew Shreve is a research scientist in image and video processing at the Xerox Research Center in Webster, N.Y. He currently works in video analytics applied to surveillance technologies. His research interests include computer vision, image processing, and pattern recognition. He holds a Ph.D. in Computer Science from the University of South Florida (2013) and a M.S. degree in Mathematics at Youngstown State University (2007). Since joining Xerox in 2011 and 2012 as an intern, and a full-time employee in 2013, Matthew has been involved in several projects including tracking the movements, body gestures, behavior, and facial expressions of customers in a retail environment, as well as outdoor vehicle monitoring that includes tracking and recognizing criminal activity such as vandalism. He also serves as an adjunct faculty member at the University of Rochester where he teaches a course on video processing. He has co-authored several conference and journal publications, and currently has 10 pending U.S. Patents.
Time: 5:00 P.M.
Date: Friday, April 11, 2014
Venue: Meshel Hall 337