VeriLook facial identification technology is designed for biometric systems developers and integrators. The technology assures system performance and reliability with live face detection, simultaneous multiple face recognition and fast face matching in 1-to-1 and 1-to-many modes.
Available as a software development kit that allows development of stand-alone and Web-based solutions on Microsoft Windows, Linux, Mac OS X, iOS and Android platforms.
The VeriLook algorithm implements advanced face localization, enrollment and matching using robust digital image processing algorithms, which are based on deep neural networks:Multiple face detection

• Simultaneous Multiple Face Processing

VeriLook 9.0 performs fast and accurate detection of multiple faces in live video streams and still images. All faces on the current frame are detected in 0.01 – 0.86 seconds depending on selected values for face roll and yaw tolerances, and face detection accuracy. After detection, a set of features is extracted from each face into a template in 0.6 seconds. See technical specifications for more details.

• Gender Classification

Optionally, gender can be determined for each person on the image with predefined degree of accuracy during the template extraction.

• Live Face Detection

A conventional face identification system can be tricked by placing a photo in front of the camera. VeriLook is able to prevent this kind of security breach by determining whether a face in a video stream is “live” or a photograph. The liveness detection can be performed in passive mode, when the engine evaluates certain facial features, and in active mode, when the engine evaluates user’s response to perform actions like blinking or head movements.

• Emotions Recognition

VeriLook can be configured to recognize emotion type in a human face. Six basic emotions are analyzed: anger, disgust, fear, happiness, sadness and surprise. A confidence value for each of the basic emotions is returned for the face. Larger value for an emotion means that it seems to be more expressed in the face.

• Facial Feature Points

The points can be optionally extracted as a set of their coordinates during face template extraction. Each of the 68 points has a fixed sequence number (i.e. number 31 always corresponds to nose tip).

• Facial Attributes

VeriLook can be configured to detect certain attributes during the face extraction – smile, open-mouth, closed-eyes, glasses, dark-glasses, beard and mustache.

• Age Estimation

VeriLook can optionally estimate person’s age by analyzing the detected face in the image.

• Face Image Quality Determination

A quality threshold can be used during face enrollment to ensure that only the best quality face template will be stored into database.

• Tolerance to Face Position

VeriLook allows for 360 degrees of head roll. Head pitch can be up to 15 degrees in each direction from the frontal position. Head yaw can be up to 45 degrees in each direction from the frontal position. See technical specifications for more details.

• Multiple Samples of the Same Face

Biometric template record can contain multiple face samples belonging to the same person. These samples can be enrolled from different sources and at different times, thus allowing improvement in matching quality. For example a person might be enrolled with and without beard or mustache, etc.

• Identification Capability

VeriLook functions can be used in 1-to-1 matching (verification), as well as 1-to-many mode (identification). The VeriLook 9.0 face template matching algorithm can compare up to 40,000 faces per second on a PC. See technical specifications for more details.

• Small Face Features Template

A face features template can be as small as 4 Kilobytes, thus VeriLook-based applications can handle large face databases. Also, 5 Kilobytes and 7 Kilobytes templates can be used to increase matching reliability. See technical specifications for more details.

• Features generalization mode

This mode generates the collection of the generalized face features from several images of the same subject. Then, each face image is processed, features are extracted, and the collections of features are analyzed and combined into a single generalized features collection, which is written to the database. This way, the enrolled feature template is more reliable and the face recognition quality increases considerably.

• More than a million algorithm deployments worldwideover the past 13 years.
• Live face detection prevents cheating with a photo in front of a camera.
• Simultaneous multiple face processing in live video and still images.
• Gender classification and age evaluation for each person in an image.
• Emotion recognition and facial feature points extraction.
• Webcams or other low cost cameras are suitable for obtaining face images.
• Available as multiplatform SDK that supports multiple programming languages.
• Surveillance SDKis available for integrating face identification into surveillance systems.
• Reasonable prices, flexible licensing and free customer support.

• National-Scale ID Projects
• Voter Registration
• Digital Identification and Certification System
• PC user authentication and file encryption
• Criminal and Forensic AFIS
• Law Enforcement and Defense Sector
• Border Control, National Security and Passport Issuance
• Time and Attendance Control

VeriLook SDK is based on VeriLook face recognition technology and is intended for biometric systems developers and integrators. The SDK allows rapid development of biometric applications using functions from the VeriLook algorithm that ensure fast and reliable face identification. VeriLook can be easily integrated into the customer’s security system. The integrator has complete control over SDK data input and output.
VeriLook SDK includes the Device Manager library that allows to perform simultaneous capture from multiple cameras. Integrators can write plug-ins to support their cameras or other devices using the plug-in framework provided with the Device Manager.
VeriLook is available as the following SDKs:

• VeriLook 9.0 Standard SDKis designed for PC-based, embedded or mobile biometric application development. It includes Face Matcher, Face Extractor and Face Verification component licenses, programming samples and tutorials, Device Manager library and software documentation. The SDK allows the development of biometric applications for Microsoft Windows, Linux, Mac OS X, iOS or Android operating systems.
• VeriLook 9.0 Extended SDKis designed for biometric Web-based and network application development. It includes all features and components of the Standard SDK. Additionally, the SDK contains Face Client component licenses for PCs and mobile / embedded devices, sample client applications, tutorials and a ready-to-use matching server

The table below compares VeriLook 9.0 Standard SDK and VeriLook 9.0 Extended SDK. See the licensing model for more information on specific license types.

Component licenses included with a specific SDK
Component types	VeriLook 9.0 Standard SDK	VeriLook 9.0 Extended SDK
• Face Verification component	1 single computer license	1 single computer license
• Face Matcher	1 single computer license	1 single computer license
• Embedded Face Matcher for Android	1 single computer license	1 single computer license
• Embedded Face Matcher for iOS	1 single computer license	1 single computer license
• Embedded Face Matcher for ARM Linux	1 single computer license	1 single computer license
• Face Client (1)		3 single computer licenses
• Embedded Face Client for Android		3 single computer licenses
• Embedded Face Client for iOS		3 single computer licenses
• Embedded Face Client for ARM Linux		3 single computer licenses
• Face Extractor	1 single computer license	1 single computer license
• Embedded Face Extractor for Android	1 single computer license	1 single computer license
• Embedded Face Extractor for iOS	1 single computer license	1 single computer license
• Embedded Face Extractor for ARM Linux	1 single computer license	1 single computer license
• Matching Server		+

(1) Face Client component includes Face Extractor, Face Token Image and Face BSS components, which can be also obtained separately.

VeriLook 9.0 SDK includes programming samples and tutorials that show how to use the components of the SDK to perform face template extraction or matching against other templates. The samples and tutorials are available for these programming languages and platforms:

	Windows 32 & 64 bit	Linux 32 & 64 bit	Mac OS X	Android	iOS
Programming samples
• C/C++	+	+	+
• Objective-C					+
• C#	+
• Visual Basic .NET	+
• Java	+	+	+	+
Programming tutorials
• C	+	+	+
• C++	+	+	+
• C#	+
• Visual Basic .NET	+
• Java	+	+	+	+

 

VeriLook SDK includes the following biometric components for face image capture, face template extraction and matching, as well as biometric standards and specific image format support.

Face Verification Component

The Face Verification component is designed for simple integration of facial recognition technology into high-security applications, like mobile banking transactions, which need only biometric identity verification. The component is intended to provide its functionality for reasonable price, especially for large-scale deployments.
The following operations are available via the high-level API:
Face enrollment into the internal database – an image with a face is captured from a camera, the face template is extracted from the image and saved into the database. Custom metainformation (like person’s name) can be provided during calling this operation to store it in the database together with the face template.
Face verification against a specific face from the database – an image with a face is captured from a camera, the face template is extracted from the image and matched against the template stored in the specified database record.
Database record removal.
Integrators can enable or disable face liveness detection to prevent fraud attempts with a photo. Also, parameters like template size or matching quality threshold can be modified before calling the enrollment or verification operations.
One Face Verification component license is included with VeriLook 9.0 Standard SDK and VeriLook 9.0 Extended SDK for all supported desktop and mobile platforms. More licenses for this component can be purchased any time by VeriLook 9.0 SDK customers.

Face Matcher Component

The Face Matcher performs facial template matching in 1-to-1 (verification) and 1-to-many (identification) modes.
The Face Matcher component matches 40,000 faces per second and is designed to be used in desktop or mobile biometric systems, which run on PCs or laptops with at least Intel Core 2 Q9400 (2.67 GHz) processor. Also the Face Matcher can be used together with Matching Servercomponent for voiceprint matching on the server-side of a client-server system.
One Face Matcher license is included with VeriLook 9.0 Standard SDK and VeriLook 9.0 Extended SDK. More licenses for this component can be purchased any time by VeriLook 9.0 SDK customers.

Embedded Face Matcher Component

The Embedded Face Matcher has the same functionality, as the Face Matcher. It matches 3,000 faces per second and is designed to be used in embedded or mobile biometric systems, which run on ARM Linux, Android or iOS devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz).
One Embedded Face Matcher license for each of Android, iOS and ARM Linux platforms is included with VeriLook 9.0 Standard SDK and VeriLook 9.0 Extended SDK. More licenses for this component can be purchased any time by VeriLook 9.0 SDK customers.

Face Client Component

The Face Client component is a combination of the Face Extractor, Face Token Image and Face BSScomponents. It is designed for the systems that need to support all functionality of the mentioned components on the same PC. Using these licenses allows to optimize component license costs as well as reduce license management.
The Face Client extracts a single face template in 0.6 seconds. The specified performance requires a PC or laptop with at least Intel Core 2 Q9400 (2.67 GHz) processor.
Three licenses for the Face Client component are included with VeriLook 9.0 Extended SDK. More licenses for this component can be purchased any time by VeriLook 9.0 Extended SDK customers.

Embedded Face Client Component

The Embedded Face Client component has the same functionality as the Face Client and is designed to run on ARM Linux, Android or iOS devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz). The component extracts a single face template in 1.2 seconds.
Three licenses for the Embedded Face Client component for each of Android, iOS and ARM Linux platforms are included with VeriLook 9.0 Extended SDK. More licenses for this component can be purchased any time by VeriLook 9.0 Extended SDK customers.

Face Extractor Component

Face Extractor creates face templates from face images. The Extractor can generalize a face template from several images that include the same face to improve the template’s quality.
Device Manager software allows to perform simultaneous capture from multiple cameras. Integrators can write plug-ins to support their cameras or other devices using the plug-in framework provided with the Device Manager.
The component extracts a single face template in 1.34 seconds. The specified performance requires a PC or laptop with at least Intel Core 2 Q9400 (2.67 GHz) processor.
One Face Extractor license is included with VeriLook 9.0 Standard SDK and VeriLook 9.0 Extended SDK. More licenses for this component can be purchased any time by VeriLook 9.0 SDK customers.

Embedded Face Extractor component

The Embedded Face Extractor has the same functionality as the Face Extractor and is designed to be run on ARM Linux, Android or iOS devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz). The component extracts a single face template in 1.34 seconds.
One Embedded Face Extractor license for each of Android, iOS and ARM Linux platforms is included with VeriLook 9.0 Standard SDK and VeriLook 9.0 Extended SDK. More licenses for this component can be purchased any time by VeriLook 9.0 SDK customers.

There are specific requirements for each platform which will run VeriFinger-based applications.
Click on specific platform to view the corresponding requirements.

Microsoft Windows Platform Requirements

• Microsoft WindowsXP / Vista / 7 / 8 / 10, 32-bit or 64-bit. If a fingerprint scanner is required, note that some scanners are supported only on 32-bit OS or only from 32-bit applications.
• PC or laptop withx86 (32-bit) or x86-64 (64-bit) compatible processors.
  • 2 GHz or better processor is recommended.
  • SSE2 support is required. Processors that do not support SSE2 cannot run the VeriFinger algorithm. Please check if a particular processor model supports SSE2 instruction set.
• At least128 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 25,000 templates (each with 2 fingerprints inside) require from 50 MB to 300 MB of additional RAM depending on configured template size.
• Free space on hard disk drive (HDD):
  • at least 1 GB required for the development.
  • 100 MB required for VeriFinger components deployment.
  • Additional space would be required in these cases:
    • VeriFinger does not require the original fingerprint image to be stored for the matching; only the templates need to be stored. However, storing fingerprint images on hard drive for the potential future usage is recommended.
    • Usually a database engine runs on a separate computer (back-end server). However, DB engine can be installed on the same computer for standalone applications. In this case HDD space for templates storage must be available. For example, 25,000 templates (each with 2 fingerprints inside) stored using a relational database would require from 50 to 300 MB of free HDD space depending on configured template size. Also, the database engine itself requires HDD space for running. Please refer to HDD space requirements from the database engine providers.

• Fingerprint reader.VeriFinger SDK includes support modules for more than 100 fingerprint scanners under Microsoft Windows platform. Integrators can also write plug-ins to support their fingerprint readers using the plug-in framework provided with the Device Manager from the VeriFinger SDK.
• Database engineor connection with it. VeriFinger templates can be saved into any DB (including files) supporting binary data saving. VeriFinger Extended SDK contains the following support modules for Matching Server on Microsoft Windows platform:
  • Microsoft SQL Server;
  • MySQL;
  • Oracle;
  • PostgreSQL;
• Network/LAN connection (TCP/IP)for client/server applications. Also, network connection is required for using Matching server component (included in VeriFinger Extended SDK). Communication with Matching server is not encrypted, therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
• Microsoft.NET framework 3.5 or newer (for .NET components usage).
• One of followingdevelopment environments for application development:
  • Microsoft Visual Studio 2008 SP1 or newer (for application development under C/C++, C#, Visual Basic .Net)
  • Sun Java 1.6 SDK or later

Android Platform Requirements

• A smartphone or tablet that is runningAndroid 4.0 (API level 14) OS or newer.
  • API level 19 is the recommendedtarget for code compilation.
  • If you have a custom Android-based device or development board,contact us to find out if it is supported.
• ARM-based5 GHz processor recommended for fingerprint processing in the specified time. Slower processors may be also used, but the fingerprint processing will take longer time.
• At least20 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 1,000 templates (each containing 2 fingerprint records) require about 2 MB of additional RAM.
• Free storagespace (built-in flash or external memory card):
  • 30 MB required for embedded fingerprint components deployment for each separate application.
  • Additional space would be required if an application needs to store original fingerprint images. VeriFinger does not require the original fingerprint image to be stored for the matching; only the templates need to be stored.
• Fingerprint reader.VeriFinger SDK includes support modules for a number of fingerprint scanners under Android platform. Integrators can also write plug-ins to support their fingerprint readers using the plug-in framework provided with the Device Manager from the VeriFinger SDK.
• Network/LAN connection (TCP/IP)for client/server applications. Also, network connection is required for using Matching server component (included in VeriFinger Extended SDK). Communication with Matching server is not encrypted, therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
• PC-side developmentenvironment requirements:
  • Java SE JDK 6 (or higher)
  • Eclipse Indigo (3.7) IDE
  • Android development environment (at least API level 14 required)
  • One of the following build automation systems:
    • Apache Maven 3.1.xor newer
    • Gradle 2.10or newer
  • Internet connection for activating VeriFinger component licenses

iOS Platform Requirements

• One of the following devices, runningiOS 8.0 or newer:
  • iPhone 5or newer iPhone.
  • iPad 2or newer iPad, including iPad Mini and iPad Air models.
  • iPod Touch 6th Generationor newer iPod.
• At least20 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 1,000 templates (each containing 2 fingerprint records) require about 2 MB of additional RAM.
• Free storagespace (built-in flash or external memory card):
  • 30 MB required for embedded fingerprint components deployment for each separate application.
  • Additional space would be required if an application needs to store original fingerprint images. VeriFinger does not require the original fingerprint image to be stored for the matching; only the templates need to be stored.
• Fingerprint reader.VeriFinger SDK includes support modules for several fingerprint scanners under iOS platform. Also, fingerprint images in BMP, JPG or PNG formats can be processed thus almost any third-party fingerprint capturing hardware can be used with the VeriFinger technology if it generates images in the mentioned formats.
• Network/LAN connection (TCP/IP)for client/server applications. Also, network connection is required for using Matching server component (included in VeriFinger Extended SDK). Communication with Matching server is not encrypted, therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
• Development environmentrequirements:
  • a Mac running Mac OS X 10.10.x or newer.
  • Xcode 6.4 or newer.

Mac OS X Platform Requirements

• A Mac runningMac OS X 10.7.x or newer. 2 GHz or better processor is recommended.
• At least128 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 25,000 templates (each with 2 fingerprints inside) require from 50 MB to 300 MB of additional RAM depending on configured template size.
• Free space on hard disk drive (HDD):
  • at least 1 GB required for the development.
  • 100 MB required for VeriFinger components deployment.
  • Additional space would be required in these cases:
    • VeriFinger does not require the original fingerprint image to be stored for the matching; only the templates need to be stored. However, storing fingerprint images on hard drive for the potential future usage is recommended.
    • Usually a database engine runs on a separate computer (back-end server). However, DB engine can be installed on the same computer for standalone applications. In this case HDD space for templates storage must be available. For example, 25,000 templates (each with 2 fingerprints inside) stored using a relational database would require from 50 MB to 300 MB of free HDD space depending on configured template size. Also, the database engine itself requires HDD space for running. Please refer to HDD space requirements from the database engine providers.
  • Fingerprint reader.VeriFinger SDK includes support modules for a number of fingerprint scanners under Mac OS X platform. Integrators can also write plug-ins to support their fingerprint readers using the plug-in framework provided with the Device Manager from the VeriFinger SDK.
  • Database engineor connection with it. VeriFinger templates can be saved into any DB (including files) supporting binary data saving. VeriFinger Extended SDK contains SQLite support modules for Matching Server on Mac OS X platform.
  • Network/LAN connection (TCP/IP)for client/server applications. Also, network connection is required for using Matching server component (included in VeriFinger Extended SDK). Communication with Matching server is not encrypted, therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
  • Specific requirements forapplication development:
    • XCode 4.3 or newer
    • wxWidgets 3.0.0 or newer libs and dev packages (to build and run SDK samples and applications based on them)
    • Qt 4.8 or newer libs, dev and qmake packages (to build and run SDK samples and applications based on them)
    • GNU Make 3.81 or newer (to build samples and tutorials development)
    • Sun Java 1.6 SDK or later

Linux x86 / x86-64 Platform Requirements

• Linux 2.6 or newer kernel (32-bit or 64-bit) is required.Linux 3.0 kernel or newer is recommended. If a fingerprint scanner is required, note that some scanners are supported only on 32-bit OS or only from 32-bit applications.
• PC or laptop withx86 (32-bit) or x86-64 (64-bit) compatible processors.
  • 2 GHz or better processor is recommended.
  • SSE2 support is required. Processors that do not support SSE2 cannot run the VeriLook algorithm. Please check if a particular processor model supports SSE2 instruction set.
• At least128 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 25,000 templates (each with 2 fingerprints inside) require from 50 MB to 300 MB of additional RAM depending on configured template size.
• Free space on hard disk drive (HDD):
  • at least 1 GB required for the development.
  • 100 MB required for VeriFinger components deployment.
  • Additional space would be required in these cases:
    • VeriFinger does not require the original fingerprint image to be stored for the matching; only the templates need to be stored. However, storing fingerprint images on hard drive for the potential future usage is recommended.
    • Usually a database engine runs on a separate computer (back-end server). However, DB engine can be installed on the same computer for standalone applications. In this case HDD space for templates storage must be available. For example, 25,000 templates (each with 2 fingerprints inside) stored using a relational database would require from 50 MB to 300 MB of free HDD space depending on configured template size. Also, the database engine itself requires HDD space for running. Please refer to HDD space requirements from the database engine providers.
  • Fingerprint reader.VeriFinger SDK includes support modules for a number of fingerprint scanners under Linux x86/x86-64 platform. Integrators can also write plug-ins to support their fingerprint readers using the plug-in framework provided with the Device Manager from the VeriFinger SDK.
  • glibc 2.11.3 library or newer
  • Database engineor connection with it. VeriFinger templates can be saved into any DB (including files) supporting binary data saving. VeriFinger Extended SDK contains the following support modules for Matching Server on Linux platform:
    • MySQL;
    • Oracle;
    • PostgreSQL;
  • Network/LAN connection (TCP/IP)for client/server applications. Also, network connection is required for using Matching server component (included in VeriFinger Extended SDK). Communication with Matching server is not encrypted, therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
  • Specific requirements forapplication development:
    • wxWidgets 3.0.0 or newer libs and dev packages (to build and run SDK samples and applications based on them)
    • Qt 4.8 or newer libs, dev and qmake packages (to build and run SDK samples and applications based on them)
    • GCC-4.4.x or newer
    • GNU Make 3.81 or newer
    • Sun Java 1.6 SDK or later
    • pkg-config-0.21 or newer (optional; only for Matching Server database support modules compilation)

ARM Linux Platform Requirements

We recommend to contact us and report the specifications of a target device to find out if it will be suitable for running VeriFinger-based applications.
There is a list of common requirements for ARM Linux platform:

• A device with ARM-based processor, runningLinux 3.2 kernel or newer.
• ARM-based5 GHz processor recommended for fingerprint processing in the specified time.
  • ARMHFarchitecture (EABI 32-bit hard-float ARMv7) is required.
  • Lower clock-rate processors may be also used, but the fingerprint processing will take longer time.
• At least128 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 1,000 templates (each containing 2 fingerprint records) require about 2 MB of additional RAM.
• Free storagespace (built-in flash or external memory card):
  • 100 MB required for VeriFinger components deployment.
  • Additional space would be required in these cases:
    • An application needs to store original fingerprint images. Note that VeriFinger does not require the original images to be stored for the matching; only the templates need to be stored.
    • Usually a database engine runs on a separate computer (back-end server). However, a DB engine can be installed on the same device for standalone applications. For example, 1,000 templates (each with 2 fingerprints inside) stored using a relational database would require about 3 MB of free storage space.
      PostgreSQL, MySQL and SQLite are supported on ARM-Linux. Please refer to hardware requirements from the corresponding database engine providers.
  • Fingerprint reader.VeriFinger SDK includes support modules for several fingerprint scanners under ARM Linux platform. Also, fingerprint images in BMP, JPG or PNG formats can be processed thus almost any third-party fingerprint capturing hardware can be used with the VeriFinger technology if it generates images in the mentioned formats.
  • glibc 2.13 or newer.
  • libstdc++-v3 4.7.2 or newer.
  • Network/LAN connection (TCP/IP)for client/server applications. Also, network connection is required for using Matching server component (included in VeriFinger Extended SDK). Communication with Matching server is not encrypted, therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
  • Development environmentspecific requirements:
    • GCC-4.4.x or newer
    • GNU Make 3.81 or newer
    • JDK 1.6 or later

These cameras are supported by VeriLook SDK:

• Anywebcam or camera that is accessible using:
  • DirectShowinterface for Microsoft Windows platform.
  • GStreamerinterface for Linux platform.
  • QuickTimeinterface for Mac platform.
• Any built-insmartphone or tablet camera that is supported by iOS or Android OS. The camera should have at least 0.3 MegaPixel (640 x 480 pixels) resolution.
• These advanced cameras are supported:
  • IrisGuard IG-AD100– face & iris camera (Microsoft Windows only)
  • VistaFA2/ VistaFA2E / VistaEY2 face & iris cameras (Microsoft Windows only)
• These models ofstill cameras are supported:
  • Canon EOS family still cameras (Microsoft Windows only)
  • Nikon DSLR still cameras (Microsoft Windows only; a specific camera model should support video capture and should be listedthere)
• Avideo file can be also used as a data source for applications based on VeriLook SDK.
• Integrators can also writeplug-ins to support their cameras using the plug-in framework provided with the Device Manager from the MegaMatcher SDK or VeriLook SDK.

Simultaneous capture from multiple cameras is possible.

High resolution cameras may be used with VeriLook, but more powerful technology like MegaMatcher SDK or SentiVeillance SDK is recommended for acceptable performance. These cameras are supported:

• AnyIP camera, that supports RTSP (Real Time Streaming Protocol):
  • OnlyRTP over UDP is supported.
  • VLCframework can be optionally used for reading video streams.
  • 264/MPEG-4 AVCor Motion JPEG should be used for encoding the video stream.
• These specific models of high-resolution cameras are supported:
  • Axis M1114 camera (Microsoft Windows and Linux)
  • Basler BIP2-1600-25c-DN IP camera (Microsoft Windows and Linux)
  • Cisco 4500 IP camera (Microsoft Windows only)
  • Mobotix S14D and DualNight M12 IP cameras (Microsoft Windows and Linux)
  • PiXORD N606 camera (Microsoft Windows and Linux)
  • Prosilica GigE Vision camera (Microsoft Windows and Linux)
  • Sony SNC-CS50 camera (Microsoft Windows and Linux)

32 pixels is the minimal distance between eyes for a face on image or video stream to perform face template extraction reliably. 64 pixels or more recommended for better template extraction results.

All face templates should be loaded into RAM before identification, thus the maximum face template database size is limited by the amount of available RAM.

VeriLook has certain tolerance to face posture that assures face enrollment convenience:

• headroll (tilt) – ±180 degrees (configurable);
  ±15 degrees default value is the fastest setting which is usually sufficient for most near-frontal face images.
• headpitch (nod) – ±15 degrees from frontal position.
• headyaw (bobble) – ±45 degrees from frontal position (configurable).
  ±15 degrees default value is the fastest setting which is usually sufficient for most near-frontal face images.

See also the whole list of recommendations and constraints for facial recognition.

VeriLook 9.0 face detection algorithm can run in maximal speed or maximal accuracy modes. The face detection times in the table below are provided for 640 x 480 pixels images as ranges, where the smallest time corresponds to the maximal speed mode, and the largest time – to the maximal accuracy. The head pitch tolerance in the table below is always ±15°.

.

VeriLook 9.0 face detection algorithm performance for all faces in a frame on PC-based systems (milliseconds)
Roll tolerance	Yaw tolerance	Intel Core i7-4771
±15°	±15°	6 – 11
±15°	±45°	10 – 23
±45°	±45°	23 – 53
±180°	±15°	53 – 132
±180°	±45°	130 – 330

VeriLook biometric template extraction and matching algorithm is designed to run on multi-core processors allowing to reach maximum possible performance on the used hardware. Face template extraction is performed after all faces are detected in a frame. The template extraction time does not depend on image size.

VeriLook 9.0 face engine specifications
	Embedded / mobile (1) platform		PC-based (2) platform
Template extraction components	Embedded Face Extractor	Embedded Face Client	Face Extractor	Face Client
Template extraction time (seconds)	1.34	1.20	1.34	0.60
Template matching components	Embedded Face Matcher		Face Matcher
Template matching speed (faces per second)	3,000		40,000
Single face record size in a template (bytes)	4,028 or 5,066 or 7,128 (configurable)

Notes:
(1) Requires to be run on iOS devices or Android devices based on at least Snapdragon S4 system-on-chip with Krait 300 processor (4 cores, 1.51 GHz).
(2) Requires to be run on PC or laptop with at least Intel Core 2 Q9400 quad-core processor (2.67 GHz) to reach the specified performance.

 

The following licensing model is intended for end-user product developers. Integrators who want to develop and sell a VeriLook-based development tool (with API, programming possibilities, programming samples, etc.), must obtain permission from Neurotechnology and sign a special VAR agreement.

Product Development

An integrator should obtain either a VeriLook 9.0 Standard SDK (EUR 339) or VeriLook 9.0 Extended SDK (EUR 859) to develop a product based on VeriLook technology. The SDK needs to be purchased just once and may be used by all the developers within the integrator’s company.
VeriLook SDKs include a number of components; each particular component has specific functionality. A license for an individual VeriLook component is required for each computer or device that run the component.
See Product Advisor to find out what specific components will be needed for your system.

VeriLook SDK components and licenses included with a specific SDK
Component types	VeriLook 9.0 Standard SDK	VeriLook 9.0 Extended SDK
• Face Verification component	1 single comp. license	1 single comp. license
• Face Matcher	1 single comp. license	1 single comp. license
• Embedded Face Matcher for Android	1 single comp. license	1 single comp. license
• Embedded Face Matcher for iOS	1 single comp. license	1 single comp. license
• Embedded Face Matcher for ARM Linux	1 single comp. license	1 single comp. license
• Face Client (1)		3 single comp. licenses
• Embedded Face Client for Android		3 single comp. licenses
• Embedded Face Client for iOS		3 single comp. licenses
• Embedded Face Client for ARM Linux		3 single comp. licenses
• Face Extractor	1 single comp. license	1 single comp. license
• Embedded Face Extractor for Android	1 single comp. license	1 single comp. license
• Embedded Face Extractor for iOS	1 single comp. license	1 single comp. license
• Embedded Face Extractor for ARM Linux	1 single comp. license	1 single comp. license
• Matching Server		+

Face Client component includes Face Extractor, Face Token Image and Face BSS components, which can be also obtained separately.
Components are copy-protected – a license is required for a component to run. License activation options are listed below on this page.
Additional component licenses may be obtained by VeriLook 9.0 SDK customers as required by their development process.

Product Deployment

To deploy a product developed with VeriLook 5.x / 9.0 SDK, an integrator need obtain only the additional licenses required for the particular VeriLook 9.0 components that will run on each computer or device belonging to their customers. The available VeriLook components and license types for product deployment are the same as for product development.
See Product Advisor to find out what specific components will be needed for the deployment of your system.
Each VeriLook component running on a computer belonging to the integrator’s customer requires a license. License activation options are listed below on this page.
Prices for VeriLook 9.0 SDK and additional VeriLook component licenses can be found here.

Licensing Agreement

The Licensing Agreement contains all licensing terms and conditions.
Note that you unambiguously accept this agreement by placing an order using Neurotechnology online ordering service or by email or other means of communications. Please read the agreement before making an order.

Single Computer Licenses

A single computer license allows the installation and running of a VeriLook component installation on one computer or device. Neurotechnology provides a way to renew the license if the computer undergoes changes due to technical maintenance.
Each single computer license requires activation for a VeriLook component to run. The available activation options are listed below on this page.
Additional single computer licenses for VeriLook components may be obtained at any time by VeriLook SDK customers.

License Activation Options

Single computer licenses are supplied in three ways:
Serial numbers are used to activate licenses for particular VeriLook components. The activation is done via the Internet or by email. After activation the network connection is not required for single computer license usage.
Notes:
Activation by serial number is not suitable for iOS and ARM-Linux platforms.
Activation by serial number is not suitable for virtual environments.
Internet activation. A special license file is stored on a computer or a mobile/embedded device; the license file allows to run particular VeriLook components on that computer or device after checking the license over the Internet. Internet connection should be available periodically for a short amount of time. A single computer license can be transferred to another computer or device by moving the license file there and waiting until the previous activation expires.
Licenses may be stored in a volume license manager dongle. License activation using volume license manager may be performed without connection to the Internet and is suitable for virtual environments.

Volume License Manager

Volume license manager is used on site by integrators or end users to manage licenses for VeriLook components. It consists of license management software and a dongle, used to store the purchased licenses. An integrator or an end-user may use the volume license manager in the following ways:

• Activating single computer licenses – An installation license for a VeriLook component will be activated for use on a particular computer. The number of available licenses in the license manager will be decreased by the number of activated licenses.
  Managing single computer licenses via a LAN or the Internet – The license manager allows the management of installation licenses for VeriLook components across multiple computers or mobile/embedded devices in a LAN or over the Internet. The number of managed licenses is limited by the number of licenses in the license manager. No license activation is required and the license quantity is not decreased. Once issued, the license is assigned to a specific computer or device on the network.
• Using license manager as a dongle – A volume license manager containing at least one license for a VeriLook component may be used as a dongle, allowing the VeriLook component to run on the particular computer where the dongle is attached.
  Additional VeriLook component licenses for the license manager may be purchased at any time. Neurotechnology will generate an update code and send it to you. Simply enter the code into the license manager to add the purchased licenses.

Enterprise license

The VeriLook enterprise license allows an unlimited use of VeriLook components in end-user products for a specific territory, market segment or project. Specific restrictions would be included in the licensing agreement.
The enterprise license price depends on the application size and the number of potential users of the application within the designated territory, market segment or project.
For more information please contact us.

Licensing old VeriLook versions – 2.0 / 3.x / 4.0

Existing VeriLook customers may also use the license management options provided for their version of VeriLook SDK:
VeriLook 3.2 / 3.3 / 4.0 SDK license management reference
VeriLook 3.0 / 3.1 SDK license management reference
VeriLook 2.0 SDK license management reference

SentiVeillance SDK – Allows to create software for performing biometric face identification and pedestrian or vehicle or other object motion tracking using live video streams from high-resolution digital surveillance cameras. SentiVeillance component is capable of performing automatic multiple face tracking, enrollment and matching against database.
MegaMatcher SDK – For development of AFIS or multi-biometric face, fingerprint, iris, voice and palm print identification products.
MegaMatcher On Card SDK –A product for face, fingerprint and iris matching on smart cards.
NCheck Bio Attendance – An end-user employee attendance management application designed as ready-to-use time and attendance system with biometric fingerprint and face identification; the application uses VeriLook facial recognition algorithm to check person identity.
NVeiler Video Filter – A plug-in for VirtualDub video processing application that is able to detect and hide faces in videos; VeriLook algorithm is used for face detection feature of the plug-in.
Check My Age – A free Android app for age estimation by face image.