|
Introduction
| Iris in an externally visible internal eye
organ that forms very early as a unique pattern (different for each eye) and
remains unchanged over time because it is well protected from the outside environment. Irises are suitable for biometric identification because of their
random variation among different eyes. They are captured at a distance, usually
in near-infrared spectral region where even seemingly dark and plain irises reveal
rich texture.
|
|
|
|
Complexity and richness of iris texture
combined with the randomness across population makes it possible to use iris
recognition in identification scenarios. An iris identification system can be
designed using:
1. a common PC, that offers enough
capabilities to perform fast iris recognition and matching,
2. a camera for scanning irises,
3. software, which can be rapidly developed
using an iris identification SDK with all necessary technologies, algorithms
and interfaces included.
Once the software is developed, the system
can be scaled up by adding more PCs, cameras and obtaining additional
technology licenses.
Neurotechnology offers iris identification
technology and SDKs that provide the needed performance and reliability.
|
The technology
VeriEye iris recognition
technology is intended for biometric systems developers and integrators.
The proprietary technology features:
• Reliability. VeriEye 2.0 algorithm shows
excellent performance when tested on all publicly available datasets.
Especially good results are achieved on the recent NIST ICE2005 Exp1 database
with iris images of intentionally degraded quality (see testing results).
• Speed. VeriEye 2.0 iris enrollment time is less
than 0.5 sec. and matching speed is configurable 50,000-150,000 irises per
second in 1:N identification mode. To confirm these results with your samples,
please try
VeriEye algorithm demo application.
• Uniqueness. The new proprietary iris
recognition algorithm is based on the original methods that solve the drawbacks
and limitations of existing state-of-the-art algorithms.
• Robustness. Eye irises are detected even
when the images have various illumination noises. Images with narrowed eyelids
or gazing away eyes are also accepted.
• Simple multi-biometric system integration.
Compatibility with fingerprint and facial identification technologies from the
same vendor allows to use VeriEye algorithm together with other
Neurotechnology's biometrical algorithms.
The SDK
VeriEye SDK is based on the VeriEye iris
recognition technology and is intended for biometric systems developers and
integrators. It allows rapid development of biometric applications using
functionality from the VeriEye algorithm, which ensures high reliability of the
iris identification, 1:1
and 1:N matching modes and comparison speeds of up to 150,000 irises per
second. VeriEye can be easily integrated into the customer's security system.
The integrator has complete control over SDK data input and output.
VeriEye SDK supports Microsoft Windows,
Linux and Mac OS X. The following types of SDK are available:
• VeriEye 2.0 Standard SDK is intended for
PC-based biometrical application development. It includes Matcher and Extractor
components, programming samples, tutorials and software documentation.
• VeriEye 2.0 Extended SDK is intended for
biometrical web-based and network application development. It includes all
features of Standard SDK. Additionally, the SDK contains sample client
applications, tutorials and a ready-to-use matching server.
Why VeriEye?
Neurotechnology started research and
development in eye iris biometrics field in 1994. In 2008, Neurotechnology has
released a PC-based iris recognition algorithm VeriEye 2.0 that is designed for
biometrical system integrators. The proprietary algorithm features:
• Reliability. VeriEye 2.0 algorithm shows
excellent performance when tested on all publicly available datasets.
Especially good results are achieved on the recent NIST ICE2005 Exp1 database
with iris images of intentionally degraded quality (see section
below).
• Speed. VeriEye 2.0 iris enrollment time is less
than 0.5 sec. and matching speed is configurable 50,000-150,000 irises per
second in 1:N identification mode. To confirm these results with your samples,
please try VeriEye algorithm demo application (see section below).
• Uniqueness. The new proprietary iris
recognition algorithm is based on the original methods that solve the drawbacks
and limitations of existing state-of-the-art algorithms.
• Robustness. Eye irises are detected even
when the images have various illumination noises. Images with narrowed eyelids
or gazing away eyes are also accepted.
• Simple multi-biometric system integration.
Compatibility with fingerprint and facial identification technologies from the
same vendor allows to use VeriEye algorithm together with other Neurotechnology's
biometrical algorithms.
• Flexible licensing and pricing. VeriEye is
offered for a competitive
price. Developers can select from several types of SDK and licensing models.
Each of these kits and models is intended for specific needs, and developers
always can make an upgrade by paying the difference between the current and
more powerful SDK.
Algorithm
The VeriEye 2.0 iris recognition algorithm
implements advanced iris segmentation, enrollment and matching using robust
digital image processing algorithms:
• Iris boundaries are not modeled by perfect
circles. Active shape models that model contours more precise are used instead,
resulting in correct iris segmentation when perfect circles fail.
• Correct segmentation when centers of iris
inner and outer boundaries are different (see Figure 1). An iris inner boundary
and its center are marked by red color; the iris outer boundary and its center
are marked by green color.
• Correct segmentation when iris boundaries
are definitely not circles and even not ellipses (see Figure 2) and especially
in gazing away iris images.
• Even when iris boundaries seem to be perfect
circles, recognition quality can still be improved if boundaries are found more
precise (see Figure 3). Note these slight imperfections when compared to
perfect circular white contours.
• Automatic interlacing detection and
correction resulting in maximum quality of iris features templates from moving
iris images.
• Elimination of lighting reflections,
eyelids and eyelashes obstructions.
• Detection and correction of gazing away
iris images (see Figure 4). A gazing away eye is correctly segmented and transformed
as it was looking directly to camera.
• Configurable matching speed varies from
50,000 to 150,000 comparisons per second. The highest speed still preserves
almost the same recognition quality (see Figure 5).
All performance evaluations were determined
for one core of Intel Core 2 Duo running at 2.66 GHz.
All iris images are taken from CASIA Iris
Image Database V2.0 and CASIA Iris Image Database V3.0 collected by the Chinese Academy of Sciences Institute of
Automation (CASIA) (http://www.cbsr.ia.ac.cn/english/IrisDatabases.asp).
Reliability Tests and Technical
Specifications
VeriEye 2.0 was tested with iris images
from several standard databases, thus the testing results can be compared with
testing results of other algorithms. Usually the algorithm recognition quality
is expressed by receiver operation characteristics (ROC) curves that show the
dependence of false rejection rate on the false acceptance rate. The presented ROC
curves show the results of testing VeriEye 2.0 with iris images from these
databases:
• CASIA Iris Image Databases V1.0 and V3.0
(interval) (see Figure 6);
• CASIA Iris Image Databases V2.0 (device1)
(see Figure 7);
• ICE2005 Exp1 iris image database (see
Figure 8).
|
VeriEye 2.0 algorithm technical specifications
|
|
Minimal radius of circle containing full iris texture
|
64 pixels
|
|
Iris rotation tolerance
|
± 15 degrees
|
|
Recommended iris image capture spectral region
|
Near-infrared
|
|
Iris template extraction time
|
0.5 sec
|
|
Matching speed
|
50,000 - 150,000 irises/sec
|
|
Size of one record in a database
|
2.3 Kbytes
|
|
Maximum database size
|
unlimited
|
These parameters were determined for one
core of Intel Core 2 Duo running at 2.66 GHz
Algorithm's Demo
|
The VeriEye demo applications for Microsoft
Windows 2000/XP/2003/Vista and Linux can be downloaded for evaluation of the VeriEye iris
recognition algorithm. The applications enroll and identify irises from image
files. Internet connection is not required to run the applications.
VeriEye 2.0 Standard SDK and Extended SDK
trials are also available for downloading. More information on obtaining CASIA iris
image databases is available on CASIA web site.
|
|
Click to zoom
|
Related Products
These products are based on the VeriEye
technology:
• VeriEye 2.0
Standard SDK;
• VeriEye 2.0
Extended SDK.
SDK Overview
VeriEye SDK is based on the VeriEye iris recognition
technology and is intended for biometric systems developers and
integrators. It allows rapid development of biometric applications using
functionality from the VeriEye algorithm, which ensures high reliability of the
iris identification, 1:1
and 1:N matching modes and comparison speeds of up to 150,000 irises per second.
VeriEye can be easily integrated into the customer's security system. The
integrator has complete control over SDK data input and output.
VeriEye SDK supports Microsoft Windows,
Linux and Mac OS X.
Contents of VeriEye 2.0 Standard SDK and
Extended SDK
VeriEye is available as the following SDKs:
• VeriEye 2.0 Standard SDK is intended for
PC-based biometrical application development. It includes Matcher and Extractor
components, programming samples, tutorials and software documentation. The SDK
allows the development of biometric applications for Microsoft Windows, Linux
or Mac OS X operating systems.
• VeriEye 2.0 Extended SDK is intended for
biometrical web-based and network application development. It includes all
features of Standard SDK. Additionally, the SDK contains a ready-to-use matching
server.
The table below compares VeriEye 2.0
Standard SDK and VeriEye 2.0 Extended SDK.
| |
VeriEye Standard SDK
|
VeriEye Extended SDK
|
|
Components
|
MS
Windows
(32&64 bit)
|
Linux
(32&64 bit)
|
Mac OS
X
|
MS
Windows
(32&64 bit)
|
Linux
(32&64 bit)
|
Mac OS
X
|
| • VeriEye 2.0 Extractor
|
1 license
|
3 licenses
|
| • VeriEye 2.0 Matcher
|
1 license
|
1 license
|
|
VeriEye Matching Server
|
|
|
|
|
|
|
| • Matching server software
|
|
|
|
+
|
+
|
|
| • Server administration tool API
|
|
|
|
+
|
+
|
|
|
• Microsoft SQL Server support module
|
|
|
|
+
|
|
|
|
• MySQL database support module
|
|
|
|
+
|
+
|
|
|
• Oracle database support module
|
|
|
|
+
|
+
|
|
|
• SQLite database support module
|
|
|
|
+
|
+
|
|
|
Programming samples
|
|
|
|
|
|
|
|
• C/C++
|
+
|
+
|
+
|
+
|
+
|
+
|
|
• C#
|
+
|
|
|
+
|
|
|
|
• C# client (for Matching Server)
|
|
|
|
+
|
|
|
|
• Visual Basic .NET
|
+
|
|
|
+
|
|
|
|
Programming tutorials
|
|
|
|
|
|
|
|
• C
|
+
|
+
|
+
|
+
|
+
|
+
|
|
• C/C++ (for matching Server)
|
|
|
|
+
|
+
|
|
|
• C#
|
+
|
|
|
+
|
|
|
|
• C# (for Matching Server)
|
|
|
|
+
|
|
|
|
• Visual Basic .NET
|
+
|
|
|
+
|
|
|
|
Documentation
|
|
|
|
|
|
|
|
• VeriEye 2.0 SDK documentation
|
+
|
VeriEye Matching Server
VeriEye Matching Server software is not
included in VeriEye 2.0 Standard SDK.
VeriEye Matching Server is a ready-to-use
software that performs the identification and verification of irises on the
server side. The server is intended to be used in web-based and other
network-based systems.
VeriEye Matching Server runs on PCs with
Microsoft Windows or Linux and includes these additional components:
• Server administration tool for monitoring
servers state, managing log and other server administration tasks;
• Support modules for MySQL, Oracle, MS SQL Server and SQ Lite
databases.
• Sample client applications:
° C# sample (for Microsoft Windows)
° C sample (for Linux)
VeriEye Extractor component
VeriEye Extractor creates iris templates
from iris images.
VeriEye Matcher component
VeriEye Matcher performs iris template
matching in 1:1
and 1:n modes.
System requirements
System requirements for VeriEye Mathing
Server
• PC with x86 compatible CPU (2 GHz processor
or better is recommended);
• UDP and TCP network support;
• MySQL, Oracle, SQLite or Microsoft SQL server (other DB servers
require a custom support module to be developed by the integrator);
• Microsoft Windows specific:
° Microsoft Windows 2000/XP/2003/Vista.
• Linux specific:
° Linux 2.6 or newer;
° GCC-4.0.x or newer;
° pkg-config-0.21 or newer;
° GNU Make 3.81 or newer;
System requirements for VeriEye Matcher and
Extractor components:
• PC or Mac with 2 GHz processor or better;
• Microsoft Windows specific:
° Microsoft Windows 2000/XP/2003/Vista
• Linux specific:
° Linux (based on glibc 2.5 or newer)
• Mac OS X specific
° Mac OS X (version 10.3.9 or newer)
SDK Trials
Neurotechnology offers VeriEye 2.0 Standard
SDK and Extended SDK on 30 day trial. The trials allow developers to explore
the SDKs' possibilities and to try them in real environments and real
applications. Constant Internet connection is required during evaluation.
VeriEye SDK trials are available for downloading.
The VeriEye 2.0 algorithm demo applications
for Microsoft Windows and Linux are also available for downloading.
Licensing VeriEye
To develop a product based on VeriEye 2.0
technology, an integrator should obtain VeriEye 2.0 Standard SDK (EUR 790) or
VeriEye 2.0 Extended SDK (EUR 1,290). Integrators can develop only an end-user
product using VeriEye SDK and sell/install the product to their own customers.
VeriEye 2.0 components are:
• VeriEye 2.0 Matcher
• VeriEye 2.0 Extractor
A license is required for each running
instance of VeriEye components. The following license types are available:
• Single
computer license.
• Enterprise
license.
VeriEye Standard SDK includes:
• 1 VeriEye Matcher license.
• 1 VeriEye Extractor license.
VeriEye 2.0 Extended SDK includes:
• 1 VeriEye Matcher license.
• 3 VeriEye Extractor license.
VeriEye 2.0 SDK customers can obtain
additional VeriEye 2.0 components licenses for their product installation or
development at any time. Prices for additional VeriEye 2.0 component licenses
can be found here.
Please also refer to VeriEye 2.0 SDK
Software License Agreement for all licensing terms and conditions.
Single computer license
A single computer license allows to install
and run a VeriEye 2.0 component installation on one processor core. Component
license will not be lost if computer will be reinstalled.
The following license management options
are available:
• license activation online by communicating
with Neurotechnology's server;
• license activation by email;
• license activation using volume
license manager;
• license management using volume
license manager on LAN or Internet.
VeriEye 2.0 enterprise license
VeriEye enterprise license allows an unlimited
use of VeriEye components (Extractor and Matcher) in the end-user products in
the certain territory, market segment or project. These limitations would be
included in the licensing agreement. For more information please contact us.
Volume license manager
Volume license manager is used on site by
integrators or end users to manage obtained licenses for VeriEye 2.0
components. It consists of license management software and a dongle, which are
used to store the number of obtained licenses. An integrator or an end-user can
use the volume license manager in the following ways:
• Activating the single computer licenses. An
installation license for a VeriEye 2.0 component will be activated for using on
a particular computer. The license quantity for the VeriEye component in the
license manager will be decreased by the amount of activated licenses.
• Managing the single computer licenses on
LAN or Internet. The license manager allows to manage installation licenses for
VeriEye components across the computers on LAN or Internet. The number of
managed licenses for a VeriEye component is limited by the number of licenses
in the license manager. No license activation is needed and the license
quantity is not decreased. Once issued, the license is assigned to certain computer
on the network.
• Using a license manager as a dongle. The
volume license manager containing at least one license for a VeriEye 2.0
component can be used as a dongle that allows to run VeriEye 2.0 component
installation on a particular computer.
Additional VeriEye 2.0 component
installation licenses for the license manager can be purchased anytime.
Neurotechnology will generate a special update file and send it to you. Then
you will just have to enter the file to the license manager to add these purchased
licenses.
* If the integrator wants to develop and
sell a VeriEye based development tool (with API, programming possibilities,
programming samples, etc.), he/she will need a permission from Neurotechnology
and shall sign a special VAR agreement.
Download
• VeriEye 2.0 Algorithm Demo (for MS Windows)
• VeriEye 2.0 Algorithm Demo (for x86-64 Linux)
• VeriEye 2.0 Algorithm Demo (for x86 Linux)
• VeriEye 2.0 Standard SDK 30 Day Trial
• VeriEye 2.0 Extended SDK 30 Day Trial
Pricing
| 
