Computational Face Group

 

The Computational Face Group is part of the Machine Perception Lab at the Institute for Neural Computation at UCSD.  This group performs computational analysis of face images for the development of computer vision systems and to model face perception in biological vision through the study of natural image statistics. A major focus of our research is the development of automatic facial expression recognition systems. We have developed an end-to-end system for automatic recognition of a set of basic expressions that works in real-time. We have also made substantial progress toward fully automating the facial action coding system, a comprehensive facial expression description system developed by Paul Ekman and Wallace Friesen. For a summary of our recent work in this area, see the following review chapter in Giese, Curio, and Bulthoff’s book on Dynamic Faces. Another focus of our research explores models of unsupervised learning and their application to face processing. For example, principles of information maximization which have been associated with neural coding in early vision, also relate to findings in human face perception, such as other-race effects, face adaptation aftereffects, and perceptual effects relating to typicality. These ideas are reviewed in a Neurocomputing 2007 paper.

 

 

People

 

Director

Marian Stewart Bartlett

 

Collaborators

Javier Movellan

Gwen Littlewort

 

Postdocs

Filippo Rossi

Josh Susskind

 

Graduate Students

Karan Sikka

Jake Whitehill

Tingfan Wu

Paul Ruvolo

Alex Ahmed

 

Undergraduates

Karmen Dykstra

Dave Deriso

Anthony Orona

 

Technical

Luis Palacios

 

Fund Manager

Kimberly Shintaku

 

 

 

 

Projects

 

 

 

 

 

The Computer Expression Recognition Toolbox

 

rep2

 

 

Information maximization, natural image statistics, and face processing

 

 

Sensorimotor learning of facial expressions: A novel intervention for autism

 

 

 

 

 

Computational Analysis of Nonverbal Behavior in Adaptive Tutoring

 

Overview_pain_system2.jpg

 

 

 

Automated detection of Pain

 

 

 

 

 

Neuroeconomics

 

 

 

 

 

Human-Robot Interaction

 

 

 

 

 

Driver Drowsiness

 

DSC05277

 

 

 

Automated Facial Expression Recognition with Application to Homeland Security

 

 

Face Recognition by Independent Component Analysis

 

Publications

 

Alumni

Esra Vural (now at Clarkson University)

Claudia Lianscsek (now at Salk)

Dirk Beer (with Don Macleod. Now at Pacific Science and Engineering, San Diego.)

Micah Eckhardt (now at MIT Media Lab graduate program)

Bret Fortenberry (now at Boston University graduate program)

Evan Smith (completed CMU graduate program, CNBC, now at Redwood Center for Theoretical Neuroscience)

Gianluca Donato (visting student from U. Padova, Italy. Now at Digital Persona, Redwood, CA.)

Andrew Salamon, Scientific Programmer