Online Commercial Assessment Process (CAP)
Tools: a Simulation
Presented by:
Martin Zeller
Date:
September 15, 2005
U S C
V I T E R B I
S C H O O L
T E C H N O L O G Y
A
N A S A
R E G I O N A L
O F
E N G I N E E R I N G
T R A N S F E R
T E C H N O L O G Y
C E N T E R
T R A N S F E R
http://www.usc.edu/go/ttc
C E N T E R
CAP Tools Website:
http://ettc.usc.edu
……
zeller
E-Motions: Facial Expression Analysis
PROBLEM ADDRESSED Facial expressions provide an important means of non-verbal communication
for humans. People are quite adept at reading facial expressions but may be expensive and/or inefficient
to employ in some situations. Machines that can be trained to analyze, interpret, advise and act on human
facial expressions could prove useful in such situations.
TECHNICAL ELEMENTS IMSC is pursuing facial expression analysis using a combination of methods. The first is a
holistic approach that looks at the full face to classify expressions. This method begins with a “training phase,” in
which a subject poses for a series of images that record a particular emotion. The holistic method is useful for
analyzing high-level expressions such as HAPPY, SAD, ANGRY, etc. The second method is more refined and
permits analysis of localized areas of the face based on actuation of facial muscles and groups of muscles. The
third is a sparse feature point analysis that can contribute to system robustness.
POTENTIAL MARKET creation of speech sequences and 2- or 3-dimensional facial animation sequences for
entertainment applications; development of 3-D avatars for advanced, virtual 3-D immersive environments;
incorporation into automated teller machines and un-staffed consumer information kiosks to improve customer
service; as a clinical aid, helping physicians and psychologists evaluate and diagnose patients
BENEFITS (1) Holistic, full-face analytical approach is effective in analyzing high-level emotions (2) local analysis
technique enables refinement of classification by correlating facial muscle contraction with local skin motion on the
face (3) muscle-based classification technique extends analysis to expressions for which the system has not been
trained (4) method can define new expressions that may be difficult for a subject to perform spontaneously (5) may
be used to classify non-emotional responses such as confusion or frustration
CONTACT Martin Zeller, USC School of Engineering Tech Transfer Center at 213-743-2927 or zeller@usc.edu
Dear:
Researchers at the University of Southern California’s Integrated Media Systems Center (IMSC) are
investigating new methods for analysis of human facial expressions. IMSC is the National Science
Foundation’s Engineering Research Center for multimedia and Internet research. IMSC is seeking
feedback on their new techniques from parties interested in the applications of facial expression
analysis. At the same time, IMSC would like to identify prospective partners who may be interested
in licensing E-Motions for commercial use.
The facial expression analysis techniques, also known as E-Motions, may have applications in the
fields of entertainment, clinical psychology, virtual immersive environments and even in customer
service. E-Motions is implemented in software and is protected by copyright.
IMSC’s facial expression anaylsis methods may prove valuable in the following commercial areas:
• Creation of speech sequences and 2- or 3- dimensional facial animation sequences
• As raw input for cloning of facial expressions from one 3-D animation model to a second,
entirely different model
• Development of 3-D avatars for advanced, virtual 3-D immersive environments
• Incorporation into automated teller machines and unattended consumer information kiosks to
improve customer service
• Clinical aid to help physicians and psychologists evaluate and diagnose patients
IMSC invites you to review the technical documentation at the link below and to provide your
feedback on the suitability of this technology to your needs. Please see:
http://ettc.usc.edu/imsc/dockets/E-Motionsdocket.pdf (PDF file) or
http://ettc.usc.edu/imsc/dockets/E-Motionsdocket.ppt (PowerPoint file)
To register your opinions on the technology or for further information please contact:
Frequently Asked Questions
From B. G., Global Network Administrator,
Zzzzzzzzzz Corporation, Las Vegas, NV
• “Can your technology be used to identify
people via video surveillance?”
The Innovators Reply
To B. G. –The IMSC researchers working on facial expression analysis
tell me that their technology _can not_ be used for
identification of people from video surveillance nor is it
intended for that purpose.
However I am aware of some technology from NASA that
might interest you. It is from NASA’s Marshall Space Flight
Center in Alabama and is called VISAR (for Video Image
Stabilization and Registration). VISAR was developed by
NASA Marshall at the request of the FBI who needed help in
analyzing the content of home video footage shot at the scene
of the bombing in Olympic Park at the 1996 Atlanta Olympics.
Frequently Asked Questions
From B. B., CTO of AAAAAAAA Co., Toronto,
Ontario, Canada
• “Thanks for your note.
The area is of interest and I will look at the
material. There is some market for this type of
technology in creating animation. However,
there are also already emerging commercial
products which do this in real time from video
analysis, i.e., without any explicit markers
added to the face, so it is not clear to me how
your technology is differentiated.”
The Innovators Reply
Dear B. B. -The innovators wanted to clarify a few points about the technology:
• The IMSC system does not require people to put marks on their
faces.
• The IMSC system also works in real-time - like others, there is
some setup required - but once you begin, the system does the face
expression analysis at 30Hz.
• Also, what differentiates the IMSC approach is the fact that it's not
based on measuring skin motion - like all others I am aware of - and it
picks up the skin creasing and wrinkle effects that these other
methods ignore.
Dr. X would be happy to discuss the details of the technology in detail
with you. They would like to invite you to visit USC for a demonstration
that will allow you to understand the approach and its implications fully.
Alternatively, for starters, I would be happy to arrange a telecon among all
interested parties to address some of these issues. Finally, you are
welcome to communicate directly with the researchers via e-mail. You
can reach them at:
Technology Analysis (Example)
Benefits
The Contactless Magnetic Slip Ring has the following
benefits when compared to conventional brush-type
slip rings:
• Contactless: Unlike conventional slip rings, this
invention has no mechanical contact between
components to degrade the operational life of the
device.
• Free of noise, no signal loss: The magnetic slip
ring transfers power that is free of noise with no
loss of electrical signal quality.
• Etc.
Technology Analysis (Example)
Competing Designs
It has come to the attention to the Far West RTTC
that the CMSR may not offer the above benefits over
competing brushless slip ring designs. Recent and
past research by the Far West RTTC has shown that
the current "state of the art" in brushless designs
have similar or exactly the same benefits as the
CMSR over brush type motors. No evidence has
been uncovered that shows the CMSR offers any
benefits over these competing designs.
Etc.
Technology Analysis (Example)
Unique Characteristics
The results from industry feedback have shown no
evidence that the CMSR technology is unique. The
Far West RTTC would need a more detailed analysis
of the technology to determine if there where any
competitive advantages over existing designs.
Information such as voltage/current capacity and cost
to manufacture are needed by industry experts in
order to determine the CMSR’s value in this
competitive market.
Etc.
Technology Analysis (Example)
Potential Commercial Applications
While researching the market for the CMSR, the Far
West generated interest from a few individuals. One
individual, Sam Yi, is starting a new company for the
purpose of developing a new type of lighting fixture
for the theatrical and entertainment industries. The
application uses a moving head luminaire, and
requires slip rings to conduct both power and data.
He required information about rough per unit costs to
manufacture for his specific application and also the
range of voltage and current that can be transferred.
Etc.
Conclusions (Example)
On the basis of feedback received from the private sector, ETTC concludes
that there is commercial interest in IMSC’s E-Motions Facial Expression
Analysis technology. This interest comes from two of the groups targeted for
input: the information kiosk industry and the animation industry. ETTC
received only one response from anyone connected with the world of
psychology. Though potentially valuable from the standpoint of possible
obstacles to implementation of the technology, the feedback does not
directly address its value for psychologists in a clinical setting.
In the worlds of information kiosks and animation, however, it appears that
there is a certain level of commercial interest that merits follow-up. Specific
contacts that are worth pursuing include:
AAAAA.org Association (Craig XXXXXXXXXX)
BBBBBBB Industries (Ben YYYYYYYY)
NNNNNNN Animation (Eric ZZZZ, John CCC, Steve GGGGGGGG)
QQQQQQQQQQ Co. (Bill PPPPPPPP)
PPPPPPPP Technologies (Sam RRRRRRRRR)
VVVVV Laboratory (John HHHHHHHH)
ETTC expects that further discussions with these groups could lead to some
form of collaboration and potential commercial application down the road.
E-Motions -- Facial Expression Analysis
A Commercial Assessment Process Phase I
Report
Prepared for
Integrated Media Systems Center
USC School of Engineering
By Martin Zeller
USC Viterbi School of Engineering
Technology Transfer Center
May 6, 2004
Table of Contents
Technology Description ……………………………………….
3
Points of Contact ……………………………………………….
4
Resources Available ……………………………………………
5
Commercialization Information and History ……………….
5
Intellectual Property Issues ……………………………………
6
Desired Commercial Outcomes ………………………………
6
Technology Docket ……………………………………………..
7
Targeted Contacts ………………………………………………
7
Industry Feedback ………………………………………………
8
Technology Analysis ……………………………………......... 13
Conclusions …………………………………………………….. 15
Remember the CAP Tools Website
http://ettc.usc.edu