FingerCell 3.1 Library SDK package

$2,658.72

Fingerprint identification for embedded platforms

SKU: NTBSDKFCLSDK101 Category:

Overview

Overview

FingerCell technology is designed for embedded biometric systems developers and features compact, sensor-independent and cross-platform fingerprint recognition algorithm. It offers decent performance, reliability and identification speed for various embedded devices based on low-power microcontrollers or processors and platforms.FingerCell is available for integrators as Software Development Kits (SDK) with FingerCell library or source code for developing a fast and reliable system on embedded or mobile platform.

  • Fast performance: Fingerprint template extraction from an image and verification against another template can be performed in less than less than 7 seconds on a 168 MHzARM Cortex-M4 family processor, which is acceptable for embedded systems.
  • Identification ability: FingerCell is suitable not only for fingerprint verification (1-to-1 matching), but also for identification (1-to-many matching). The algorithm matches about 250 fingerprints per second in 1-to-many mode on a 168 MHz ARM Cortex-M4 family processor.
  • Adaptive image filtration: This algorithm eliminates noises, ridge ruptures and stuck ridges for reliable minutiae extraction even from poor quality fingerprints.
  • Compact fingerprint template: FingerCell template size depends on the number of stored minutiae – for example, a template with 16 minutiae needs only 152 bytes of memory, whereas a template with 64 minutiae needs 448 bytes. Combined with configurable maximal number of minutiae in a template and unlimited database size, the target system size and performance can be optimized according to customers requirements.
  • ANSI and ISO/IEC standards support: FingerCell SDK can generate and match fingerprint templates in the ISO/IEC 19794 and ANSI/INCITS 378 family formats
  • Tolerance to fingerprint translation and rotation.Such tolerance is achieved by FingerCell proprietary fingerprint matching algorithm. The algorithm is able to identify fingerprints even if they are rotated and translated.
  • Compact portable software: FingerCell is designed for easy implementation into very various and specific applications. The algorithm’s source code is sensor independent; therefore it can be ported to various platforms and hardware. Compiled code and internal data arrays require only 128 kB of memory and therefore can be implemented in low memory microchips, thus reducing hardware costs.
  • FingerCell Demo Unit: Neurotechnology offers pre-installed FingerCell algorithm on testing hardware for the technology evaluation. The Demo Unit is available on request.

Highlights

Highlights

  • Fast performance even on low speed processors.
  • Verification (1-to-1 matching) and identification (1-to-many matching) are provided.
  • Compact fingerprint template and unlimited database size.
  • ANSI and ISO biometric standards support.
  • Cross platform algorithm with compact portable source code.
  • FingerCell Demo Unit with pre-installed algorithm is optionally available.
  • Reasonable prices, flexible licensing and free customer support.

Use Cases

Use Cases

  • FingerCell can extract a fingerprint template using less than 128KB of memory, enabling it to be used in compact devices that have limited on-board resources, such as:
    • mobile phones,
    • fingerprint door locks,
    • access control panels,
    • time and attendance systems,
    • handheld payment and
    • point-of-sale terminals.
  • It can also be used in various logon subsystems and small device components that can be integrated into cars and home electronics, among others.

System Architecture

System Architecture

Different embedded biometric projects may have specific requirements for system architecture. The components of FingerCell SDK provide interoperability with other Neurotechnology biometric SDKs or third party products and are designed for using in different scenarios:

  • Template extraction and matching on embedded device: This scenario offers privacy and security, as biometric templates do not leave the device. All functionality can be implemented using only FingerCell SDK and its components, without the need to use any other products. Note, that an embedded device should provide enough computational resources to perform all operations in reasonable time.
  • Template extraction on embedded device, template matching on smart card: In this scenario, privacy and security is achieved by smart card usage for identity verification, as biometric information is only transferred from embedded device to smart card and is not exposed. Smart card matching technology is not included in the FingerCell SDK. These technologies can be used:
    • MegaMatcher On Card SDKis our multi-biometric mathing-on-card technology, which is compatible with fingerprint templates generated by FingerCell SDK.
    • Other vendors’ matching on card technologies, which accept biometric templates in ISO/IEC 19794-2 format.
  • Template extraction on embedded device, template matching on server or cloud: In this scenario, an embedded device, which runs FingerCell algorithm, performs fingerprint template extraction and sends the fingerprint template to a server or cloud for matching. These server-side template matching technologies may be considered, if a system includes large biometric database or should feature high performance:
    • VeriFinger SDKand MegaMatcher SDK are our biometric identification technologies, which are compatible with fingerprint templates generated by FingerCell SDK and include ready-to-use components for server-side template matching.
    • Other vendors’ server-side fingerprint matching technologies, which accept biometric templates in ISO/IEC 19794-2 or ANSI/INCITS 378 formats.
  • Template extraction on PC or mobile device, template matching on embedded device: In this scenario, an embedded device, which runs FingerCell algorithm, accepts fingerprint templates for further matching. Fingerprint templates can be generated using these technologies:
    • VeriFinger SDKand MegaMatcher SDK are our biometric identification technologies, which include components for fingerprint template extraction on Microsoft Windows, Mac OS X, iOS, Android, Linux x86/x86_64 and ARM Linux platforms. The components can be configured to generate fingerprint templates which are compatible with FingerCell SDK.
    • Other vendors’ server-side fingerprint matching technologies, which generate biometric templates in ISO/IEC 19794-2 or ANSI/INCITS 378 formats.

SDK Contents

SDK Contents

FingerCell 3.1 SDK is based on FingerCell 3.1 technology that is specially designed for integrating biometric fingerprint recognition into hardware with low-power, low-memory microcontrollers. The fingerprint templates created with FingerCell SDK are compatible with VeriFinger SDK, MegaMatcher SDK and MegaMatcher On Card SDK biometric technologies. Also, FingerCell SDK is compatible with third-party biometric systems, as it accepts and generates fingerprint templates in ISO/IEC 19794-2 and ANSI/INCITS 378 formats.The following types of FingerCell 3.1 SDK are available:

  • FingerCell 3.1 Library SDK– Provides the FingerCell components as a static library, which is compiled for required platform. The SDK also includes documentation with programming samples and tutorials. See also the licensing model.
  • FingerCell 3.1 Source Code SDK– Provides the FingerCell components as source code, which is intended for porting into required platform. The SDK also includes full documentation for the source code. See also the licensing model.

The FingerCell SDK components provide this functionality:

  • Fingerprint template extraction:-The component creates fingerprint templates from fingerprint images which are provided to the component by integrators. Fingerprint templates can be stored in the following formats:
    • Neurotechnology proprietary fingerprint template format;
    • ISO/IEC 19794-2:2005with  1:2009 (General and On-Card Fingerprint Minutiae Data Formats);
    • ISO/IEC 19794-2:2011with  1:2012 (General and On-Card Fingerprint Minutiae Data Formats);
    • ANSI/INCITS 378-2004(Finger Minutiae Format for Data Interchange);
    • ANSI/INCITS 378-2009with  1:2010 (Finger Minutiae Format for Data Interchange).
  • Fingerprint template stitching: The component combines multiple fingerprint templates into a single template, which can significantly improve recognition accuracy. The template stitching algorithm is specially designed for use with small area sensors.
  • Fingerprint template matching:Template matching can be performed in 1-to-1 (verification) and 1-to-many (identification) modes. The component accepts fingerprint templates in the following formats:
    • Neurotechnology proprietary fingerprint template format;
    • ISO/IEC 19794-2:2005with  1:2009 (General and On-Card Fingerprint Minutiae Data Formats);
    • ISO/IEC 19794-2:2011with  1:2012 (General and On-Card Fingerprint Minutiae Data Formats);
    • ANSI/INCITS 378-2004(Finger Minutiae Format for Data Interchange);
    • ANSI/INCITS 378-2009with  1:2010 (Finger Minutiae Format for Data Interchange).

System Requirements

System Requirements

 

There are specific system requirements for evaluating FingerCell technology, developing a FingerCell-based solution and deploying it on embedded hardware. Click on specific platform to view the corresponding requirements.

Technology Evaluation and Development 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 FingerCell 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, 10,000 templates (each with 1 fingerprint inside) require from 10 MB of additional RAM depending on configured template size.
  • Fingerprint reader (optional). The trial version of FingerCell SDK includes support modules for more than 100fingerprint scanners and sensors under Microsoft Windows platform. Also, fingerprint images in BMPJPG or PNG formats can be provided to the FingerCell algorithm for evaluation.
  • Network/LAN connection (TCP/IP)for client/server applications. 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).

Deployment Platform Requirements

  • A device with ARM-based microcontroller:
    • ARMCortex-M4 based microcontroller, running at 168 MHz or better recommended for performing template extraction and matching in the specified time.
    • Floating Point Unit (FPU) is not required for the FingerCell algorithm.
    • Slower microcontrollers may be used if a system uses smaller fingerprint images or has lower performance requirements.
  • Memory requirements depend on a specific operation performed with fingerprint templates. Note that RAM is mostly used only during operation and is freed aftewards, so it can be reused for another operation:
    • Template extraction from an image requires 128 kB of RAM and 100 kB of Flash
    • Templatematching requires 16 kB of RAM and 70 kB of Flash
    • Templatestitching requires 50 kB of RAM and 80 kB of Flash  This RAM amount is required for performing the operation with 9 templates.
    • Additional flash storage is required for systems that store multiple fingerprint templates.
    • Additional RAM is required for systems that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. See technical specifications for more information.
  • FingerCell technology can be deployed on different platforms, which can be with or without operating system. However, FingerCell libraries require some functions from the standard C library: malloccallocreallocfreememcpymemcmpmemsetmemmoveqsortpow. These functions should be provided by the integrators.
  • Fingerprint readers and fingerprint images:The FingerCell Extractor component directly accepts fingerprint images as raw grayscale pixels for further biometric template extraction, thus almost any fingerprint sensor can be used.
    • Integrators should implement by themselves the passing of fingerprint images to a device which runs the FingerCell algorithm.
    • The fingerprint images should meet thetechnical specifications for acceptable fingerprint recognition performance on a target device.

Technical Specifications

Technical Specifications

 

385 ppi is the minimal recommended fingerprint image resolution for FingerCell template extraction algorithm.
If the system needs to perform person’s identification (1-to-many matching), all fingerprint templates should be loaded into RAM, thus the maximum fingerprint templates database size is limited by the amount of available RAM. See system requirements for more information about the required amounts of RAM and flash storage.
The performance specifications below are provided for embedded hardware based on ARM Cortex-M4F microcontroller, running at 168 MHz clock rate.

FingerCell 3.1 algorithm technical specifications
Template extracion time (milliseconds) (1) 650
Template stitching time (milliseconds) (2) (3) 600
Template verification time (milliseconds) (3) 4
Template identification speed (templates per second) (3) 250
Template size with 16 minutiae (bytes) (4) 152
Template size with 64 minutiae (bytes) (4) 488


Notes:

  • For performing the operation with 180 x 256 pixels fingeprint images at 385 ppi resolution, or, correspondingly, 234 x 332 pixels at 500 ppi.
  • For performing the operation with 9 fingerprint templates.
  • For templates containing up to 64 minutiae.
  • The template size depends on the actual number of minutiae stored in it. The provided values are reference sizes for the corresponding numbers of minutiae.

Licensing Model

Licensing Model

FingerCell 3.1 SDK is offered in the following options:

  • Library license.The Library license is a royalty based license which allows usage of FingerCell static library for the end user products as long as required amount of installation licenses is obtained. The installation licenses are per embedded device, however, no activation on particular device is needed – FingerCell usage and deployment are controlled by licensing agreement. The installation licenses are obtained in advance and their usage is reported.
  • Library Enterprise license:The Library Enterprise license allows unlimited usage of FingerCell static library for the end user products for just one time EUR 150,000 payment.
  • Source code license:The Source code license covers source code of FingerCell algorithm and allows unlimited usage of FingerCell for the end user products for just one time EUR 250,000 payment.

Integrators should sign the FingerCell 3.1 SDK Software Licensing Agreement before purchasing FingerCell 3.1 SDK.

Related products

You may also like…