SUNNYVALE, CA — (MARKET WIRE) — 02/27/2006 — A4Vision Inc. today
announced that the company has entered into a strategic OEM relationship
with Motorola, Inc (NYSE: MOT). A4Vision will provide its patent pending
2D/3D ICAO compliant camera and award-winning 3D facial recognition software
to Motorola as a key software and hardware option. The technology is
featured in Motorola’s Identity Management and Security Solutions Portfolio,
a complete document management and biometrics identification system for
enrollment and issuance of secure national ID cards and passport documents.

Driven by terrorist threats, governments worldwide are implementing programs
with secure biometric ePassports and National ID cards to make travel safer.
Motorola’s solution enables the creation of ICAO-compliant machine readable
travel documents with fingerprint and facial biometric data stored directly
on the documents for highly accurate user authentication at various
checkpoints, borders, and other points of entry. A4Vision’s 3D facial
technology provides a powerful tertiary biometric to compliment Motorola’s
leading fingerprint technology. The 3D facial technology makes it easy to
enroll people and to verify one’s identity at a border. Citizens also
benefit from the reduction of identity theft and fraud.

A4Vision’s 3D facial technology and cameras combined with face/finger fusion
contribute to Motorola’s portfolio as one of the most accurate in the
industry,” said Darrin J. Reilly, General Manager of Motorola’s Biometrics
Unit. “Motorola’s Biometrics Identity Management and Security Solutions
Portfolio illustrates our expertise in fusing multiple biometrics onto smart
cards and secure documents such as ePassports.”

“Motorola is among the most prominent innovators in using biometrics for
identity management, and with the inclusion of A4Vision’s technology in
Motorola’s Biometric Identity Management and Security Solutions, Motorola
illuminates the value of 3D facial biometrics to the security industry,”
said A4Vision CEO Grant Evans. “A4Vision’s technology contributes to a
safer, faster, and more successful travel experience, while elevating
security control for the global community.”

A4Vision’s 3D/2D biometric cameras, combined with smart cards and secure
documents, achieve superior speed and accuracy in border control.

3D Facial

The Biometric Facial Scan
The study of face recognition has received great attention from the computer
vision community. Humans detect and identify faces in a scene with little or
no effort. However, building an automated system to accomplish this task
introduces some difficulties.

The need for a facial recognition system, which is both reliable and
non-intrusive, has been sharply increased by wide scale public demand for
more effective criminal identification and monitoring systems. Additionally
there are new incentives to invest in security infrastructure by government,
law enforcement agencies and corporations.
Biometric facial scan is the only means to meet emerging public safety
needs. Unlike any other biometric technologies - such as fingerprint or iris
recognition - facial scan is able to function in a real-time environment,
requiring no cooperation or awareness from the subject. It is therefore
suitable for non-intrusive security checks at high-risk public sites
(airports, borders, etc), and for passive identification and monitoring of
known criminals and terrorists.

The Face Recognition System
A4Vision provides the core technology required for an end-to-end biometric
system as shown in Figure 1. This consists of modules for a) the acquisition
of the 3D data; b) data processing where the 3D surface is reconstructed for
further recognition; c) creation of the biometric template from the
extracted feature and d) the eventual matching (recognition) based on a
comparison of acquired and previously enrolled biometric templates.

Face Capturing
A4Vision’s proprietary hardware for face capturing - or the acquisition of
facial data - works on the principle of structured or coded lighting. The
essence of structured lighting consists in projecting a pattern of known
space structure at the subject’s face. The structured light is distorted by
the individual facial geometry, and these distortions are unambiguously
defined by the form of the scanned surface. Having defined compatibility
between elements of the initial and determined structure of the coded light
beam, by means of reconstruction algorithms, it is possible to precisely
restore the geometry of the registered surface.

Face capturing refers to the moment when the camera and the special light
take a “picture” of the target. This module includes the software necessary
to automate the acquisition process by mean of PCs. The software controls
the hardware functionality and synchronizes all the necessary steps of the
acquisition process.
A simplified scheme on how the capturing works is represented in the
following figure:

3D Reconstruction
The second step is the reconstruction of the 3D surface illustrated in
Figure 3 below. This module uses a set of proprietary algorithms, designed
for surface reconstruction and optimization, based on data received from the
camera. After receiving raw data (the distorted pattern on the target
object), the 3D Reconstruction algorithms perform image filtering (noise
reduction), and then instantly reconstructs the 3D surface, smoothing and
interpolating data to avoid holes and optimizing the mesh.

The algorithm has to recognize the pattern projected onto the surface and
calculate, by means of triangulations, all three coordinates of the sampled
points on the surface. This will result in the surface described in the form
of a cloud of points. After this step, the system will interpolate all the
points by mean of a mesh.

Next, if the color surface was captured by an A4Vision enrollment device,
the surface can then be calculated and over-imposed onto the mesh. The
texture can be overlapped (after an automatic adaptation) on the 3D surface.
This stage is not relevant for devices using the 3D video unit, where the
surface texture is not captured.

It is important to stress that the texture is NOT needed for recognition
purposes. The output of this module is the optimized 3D surface or 3D mesh,
suitable for further use in the recognition process.