|
May 15, 2002
Facial-Recognition
Solutions Roundup
Facial-recognition biometric technologies are becoming more and more
popular as a way to verify and identify individuals for secure physical
and logical access. But they also serve as a way to pick a face out of a
crowd, an invaluable tool when searching for wanted criminals, runaway
children, and other individuals who might otherwise be needles in a
haystack.
Many of today's image acquisition and recognition technologies and
systems can zero in on faces from live video feed and still photographs,
and can then perform one-to-one or one-to-many searches through a
database of faces, searching for a match. Solutions offer a vast array
of options for storing enrollment templates locally or across a network,
and verification and identification techniques take no more than a few
seconds.
This roundup should serve as a starting point as you research
facial-recognition biometric solutions, and includes information on
technologies and algorithms for performing recognition, systems and
software that offer identification and verification, and software that
enables database searching and comparison. Many technology vendors also
offer software development kits allowing developers to create their own
applications and systems. This roundup is in no way a comprehensive guide,
and we were not able to include every company in this space. If your
company was not included in this guide, feel free to e-mail Laura
Guevin with information for future roundups.
AcSys
FRS product line
AcSys
Biometrics Corp.
399 Pearl
St.
Burlington, ON
L7R 2M8 Canada
Contact: Ashley
Kelly
877-842-7687 x28
The AcSys FRS product line is based on the companys Holographic
Neural Technology (HneT) technology, which is modeled on the workings of
the human brain. The technology defines how single neuron cells are
capable of learning stimulus-response memories in real time, and enables
a synthetic neuron cell to learn tens of thousands of stimulus-response
memories in less than a minute, and respond to tens of thousands of
stimulus patterns in less than a second.
The
technology has been used in the AcSys FRS Entry product, an access
control solution that learns individuals faces each time they pass
through, adjusting for seasonal changes, aging, and variations in
cosmetics. The AcSys FRS Logon IT security product replaces passwords
with users faces for the Windows logon process, while the AcSys FRS
CoLo product controls access to servers at the cabinet level. It logs
all access attempts along with the images of the user or suspected
intruder, and supports one-to-one verification and one-to-many
identification.
SecureIDent
Products
BioDentity
Systems Corporation
160 Michael Cowpland Dr.
Ottawa, ON Canada K2M 1P6
613-270 9822
The BioDentity family of SecureIDent products
encompasses everything from hardware to middleware to specialized
application software. The PreProcessor offers comprehensive facial
capture and image recognition support regardless of lighting and other
environmental factors. It separates the facial image from the background
for easy processing of information, and automatically tracks, zooms, and
captures anyone within a three-dimensional plane.
The
SecureIDent PreProcessor offers onboard processing, and can provide
front-end enhancement to any other facial-recognition system or
application. Other offerings in the family include the SecurIDent Face
Recognition Controller, which is the primary interface between the
PreProcessors and the rest of the application; the SecurIDent Photo
Enrolment System, which automatically optimizes all images to create a
high-quality database; and the SecurIDent Search Engines, which compare biographical or face biometric details, or a combination of the two,
against very large databases.
Single
Sign-On
BioID
America Inc.
920 Main Campus Dr., Ste. 100
Raleigh, NC 27606
919-424-4550
866 GoBioID
BioIDs
Single Sign-On (SSO) technology offers the ability to analyze face,
voice, and lip movement simultaneously, and requires only a standard USB
camera and microphone for implementation. Users look into the camera and
speak a phrase for verification, offering a single ID for signing on to
applications or gaining access to an area.
The solution can be integrated with the BioID
Face Database, which allows researchers to compare the quality of their
face detection algorithms with others. The BioID dataset features 1,521
gray level images showing a frontal view of a face of one out of 23
different test persons. Images are stored in single files using portable
graymap (pgm) data format.
FaceVACS-Logon
Cognitec
AG
1018 Hemlock St.
Lake Oswego, OR 97034
503-675-9955
The FaceVACS-Logon system offers automatic facial identification, and
may be combined with the input of a password. It may be integrated with
conventional access control or time and attendance systems, and a
combination with card terminals is possible for high-security areas.
Users faces are captured by video camera, and image-processing
algorithms extract a feature set from the digitized image, which the
software compares to the users reference set, stored on the computer.
Features of the system include flexible operating modes, which enable it
to be used as a stand-alone facial-recognition solution or in
combination with a password, and facial recognition is performed at
logon, to unlock the screen lock and screen saver. Other features
include a morphing editor for the built-in screen saver, standard Webcam
support, and support of Windows 98/2000/NT/XP/Me.
FaceTrac
Graphco
Technologies, Inc.
41
University Dr., Ste. 205
Newtown, PA 18940
215-497-9170
The
FaceTrac facial-recognition system is geared toward law enforcement and
private security agents, and offers image capture, comparison against
images in a database, and matching of images. This open system can
enhance existing surveillance installations, and can incorporate
facial-recognition engine components from leading vendors like Viisage,
Visionics, and AcSys Biometrics.
The
system is part of the Bastille product family, which is centered on a
highly secure, criminal intelligence information sharing system. The
solution aggregates, disseminates, and secures case information among
member law enforcement agencies, and makes all member PCs points of
access for law enforcement data and communications. FaceTrac can match
the facial geometry of an individual against suspects portraits in
the Bastille database.
True
ID
Identico
Systems
15 Charron Ave.
Nashua, NH 03063
888-878-3438
The
True ID services from Identico offer real-time image verification to
protect businesses and consumers from identity-based fraud. Services may
be integrated into most existing transaction processing systems, and
works by electronically scanning a customers photo ID. Data is
encrypted and transmitted to an Identico database, and it is stored and
mapped to the customers financial payment and transaction data there.
The customers image is then securely transmitted to the point of
service during the next transaction for instant identity verification.
Features include strong
encryption technology to protect the entire ID collection and storage
process, and images may only be decrypted and displayed at the point of
service. The service also offers innovative data collection and receipt
retrieval procedures to deter chargeback and return frauds, while
internal transaction frauds may also be reduced through secure employee
sign-on procedures.
Face
ID
ImageWare
Systems, Inc.
10883 Thornmint Rd.
San Diego, CA 92127
858-673-8600
ImageWares Face ID facial-recognition program is aimed at law
enforcement officials, and enhances their ability to identify suspects.
The system uses biometrics in combination with parallel processing to
identify suspects through a mathematical formula that uses the eyes as a
reference point. The formula generates a data record representing the
face, which is used to compare against a digital database of enrolled
images.
Images
from scanned photographs, mugshots, suspect composites, or video
surveillance may be queried using the program, and millions of images
may be searched to identify unknown suspects, as well as criminals with
multiple aliases. The recognition program is resistant to changes in
facial expression, hairstyles, disguises, lighting, and pose variations
of up to 35 degrees in all directions. It may be used with ImageWares
Crime Capture System or another photo database for comparison, and can
also interface directly with ImageWares Suspect ID composite software
to search for matches.
ID-2000
Imagis
Technologies Inc.
1075
West Georgia St.
Ste. 1300
Vancouver, BC Canada V6E 3C9
604-684-2449
Using
more than 200 facial descriptors generated from an image analysis
algorithm, the ID-2000 software captures, compares, and quickly and
efficiently displays an individuals face against a database. It
enables an individual to be identified in seconds using only an image or
photograph as the primary search criteria. And links allow the database
to be mined to display additional details like aliases, vehicles,
associates, and images of distinguishing features like marks, scars, and
tattoos.
The software may be
integrated with any Imagis software products, including the companys
Computerized Arrest and Booking system (CABS), Secure-ID, and Envisage
applications. It may also be embedded into existing access control
applications or secure databases combined with encryption protocols or
other biometrics, utilizing the companys SDK.
IRID
Infrared
Identification Inc. (IRID)
PO Box
7025
Fairfax Station, VA 22039-7025
703-690-1234
The
IRID face-recognition technology has been developed as part of a
partnership between IRID and Mikron
Instrument Company. The solution can perform infrared facial
recognition as well as continuous condition monitoring of individuals by
using passive infrared imaging that is non-contact, non-invasive, and
works under any lighting conditions or in total darkness.
IRID
offers automatic, continual validation that a person is alive, present,
awake, alert, and attentive. The company is using the technology to
update the prototype access control system it has been developing for
more than 25 years.
Tridentity 3
Dimensional Face Recognition
Neurodynamics
Limited
Cambridge Business Park
Cowley Road
Cambridge CB4 0WZ UK
+44(0)1223-488540
The
Tridentity system offers a three-dimensional approach to facial
recognition, and can analyze subtle features of the face like bone
structure, and enables images to be rotated to offer a better view of
the subject. The technology uses patterned light to create a
three-dimensional image of the face, and once an image is captured, a
3-d representation of the subjects face can be built from a single
frame of video footage.
The
solution can operate on single or multiple scans, and each scan can be
processed in under one second on a 400 MHz Pentium system. The search
database size is limited by disk space and processor speed only, and the
system may be expanded to scale up to multiple cameras and workstations.
The system is based on an open architecture, uses COTS components, and
may be easily integrated as a component of a larger system.
QuadHDTV
Video Image Sensor
Photon
Vision Systems, Inc.
Finger
Lakes Business and Technology Park
One
Technology Place
Homer,
NY 13077
607-756-5200
This
image sensor and camera development platform is based on Photon
Visions Active Column Sensor (ACS) technology, and has been
integrated into
JVCs
Ultra High Definition TV color
camera. The sensor may be used for applications requiring computer
recognition of individual faces or other features, and offers
low-noise video and the PVS-Bus technology for high-speed video data
rates.
Additional
features include 60 fields/second interlaced and 30 frames/second
progressive video, compatibility with 35mm optics, on-chip correlated
double sampling, on-chip integrated timing and control logic, a single
five-volt power supply, and simple clocking. The color version of the
image sensor meets the requirements for biometric applications as well
as digital cinematography, broadcast video, and high-end security and
surveillance applications.
FaceOn
Symtron
Technology
710
Lakeway Dr., Ste. 240
Sunnyvale, CA 94086
408-738-6888
The
FaceOn technology uses neural network and artificial intelligence
techniques to capture faceprints and determine or verify identity. It is
at the core of all Symtron offerings, including the FaceOn Logon
product, which protects proprietary data on a computer by requiring a
users face for logon.
The
FaceOn Logon AdminTool enables users to set up security preferences and
complete the faceprints enrollment process easily, as well as add and
delete faceprints from the database. The enhanced visual Access Log
enables administrators to keep tack of all users access settings. The
FaceOn Surveillance system may be integrated with various types of CCTV
systems, and offers multiple, real-time image enrollment, retrieval, and
recognition (using the Invariant Feature Analysis technology). The
FaceOn Law Enforcement system enables law enforcement officials to build
up a digital faceprint database and search, verify, and identify
suspects through it. It may be integrated with existing law enforcement
information systems, and enables users to search, record, track, and
report records.
FR
Technology
Viisage
Technology, Inc.
30 Porter Rd.
Littleton, MA 01460
978-952-2200
The Viisage
face-recognition (FR) technology is based on an algorithm developed at
MIT, and enables the companys software to translate the
characteristics of a face into a unique set of numbers called an
eigenface. This is used by identification and verification systems for
facial comparisons made in real time, and may be used with databases
containing millions of faces. The technology enables software to
instantly calculate an individuals eigenface from live video or a
still digital image and then search a databased to find similar or
matching images.
The companys family of products is made up of
the FaceFINDER, FaceEXPLORER, FacePASS, FacePIN, and FaceTOOLS
applications. They offer: Surveillance for law enforcement, the ability
to search large databases of images, identity and authorization for PCs,
mobile, and Internet applications as well as for physical access and
keyless entry, security at retail locations and ATMs, and a software
development kit (SDK) for developing additional applications.
FaceIt
Visionics
Corporation
One Exchange Place
Jersey City, NJ 07302
201-332-9213
The
FaceIt facial-recognition software engine from Visionics enables
computers to rapidly and accurately detect and recognize faces, for
everything from ID solutions to banking and e-commerce applications. The
software can detect one or multiple faces, and can also provide
one-to-one or one-to-many matching. It also evaluates the quality of the
image and prompts for an improved image if needed, and can crop faces
from background imagery.
Other
features include the ability to generate a faceprint, a digital
code/template unique to an individual, as well as the ability to track
faces over time. FaceIt can also compress facial images to 84 bytes for
easy storage and transfer. It uses the local feature analysis technique
to represent facial images in terms of local, statistically derived
building blocks. The software is resistant to changes in skin tone,
lighting, facial expression, eyeglasses, and hair, and allows up to 35
degrees of change in pose in all directions.
UnMask
Visionsphere
Technologies Inc.
Building M-50
National Research Council
1200 Montreal Rd.
Ottawa, ON Canada, K1A 0R6
613-740-0245
The UnMask system offers face detection and location of key features,
extraction of facial descriptors, and comparison of extracted
information against a database. It locates the face and the eyes
automatically through proprietary search algorithms, and then normalizes
and crops the image to offer invariance to variations in head rotation,
lighting, hairstyle, and facial expression. The system then uses
VisionSpheres Holistic Feature Code (HFC) to provide discrimination
for comparing faces at high confidence rates and fast processing speeds.
Faces are then compared using a proprietary distance function, which
stresses significant differences between faces.
VisionSphere
also offers the UnMask Plus software artificial intelligence (AI)
system, which provides identification and removal of duplicate or
multiple images from large databases. The Its Me advanced automatic
computer logon authentication system offers hardware and software
components for verifying the identity of a network or workstation user.
And the FaceCam biometric user-verification terminal offers integration
with applications for physical access control, time and attendance, and
registration systems.
ZN-Face
ZN
Security,
a division of ZN Vision Technologies AG
Universittstrasse 160
44801 Bochum, Germany
49-234-9787-0
The
ZN-Face physical access control system enables automation of identity
checks for access to secure areas. Available in single and multiple
station versions, the system may be fully integrated with existing
access control and time attendance systems. It automates identity checks
by taking a picture of the individual requiring access, and recognizing
that image to enable access. The system uses a neural face-recognition
routine to verify individuals, and also offers a refined optical filter
system and a LiveCheck analysis procedure to prevent attempts at
spoofing through photos or masks.
The
system may be administered via Windows NT/2000, and can be tailor-made
to suit the needs of a business. It supports the ODBC database interface
standard to enable acceptance of the master data from external
databases, and also features the ZN-SmartEye technology. This enables
evaluation of pictures from one or several video cameras, and reports
the appearance of a known face for tracking guests and protecting safety
areas. The system also works with ZN-Phantomas, a computerized image
database that can automatically compare and identify faces.
|
