Bioscrypt Embedded Solutions MV1200 MV-Lite OEM Modules

Bioscrypt Core Verification Library

Call or Email for Price Info

Bioscrypt Core Verification Library
Bioscrypt's verification library, Bioscrypt Core, is a sophisticated, state-of-the-art algorithm for comparing fingerprint images. It is at the heart of all Bioscrypt product offerings and is also available for license.

Bioscrypt Core is proven technology. It is the engine behind the over 50,000 Bioscrypt physical access products that have been deployed to organizations such as NASA, New York Police Department, American Express, E*Trade, and Continental Airlines. It is at the heart of over 100,000 Network Access stations, including Targus fingerprint capture devices. Additionally, Bioscrypt Core has been selected by various fingerprint sensor manufacturers such as Atmel, Authentec and Fidelica, and application developers such as Indivos and Sense Technologies.

Flexibility of the Bioscrypt Core Verification Library:

Bioscrypt Core can be customized for particular applications, taking into account platform requirements, security concerns, template size restrictions, search speed, and database size requirements. The options include:

Platform Interoperability of the Bioscrypt Core Verification Library:

Bioscrypt Core has been specifically designed to be portable and has been successfully deployed on numerous operating systems and processing architectures. The library is available under Windows, Windows CE, and Linux, as well as for many popular Digital Signal Processors. The Bioscrypt team has extensive experience with both PC and embedded software development. Over the past six years Bioscrypt has developed products using Texas Instruments, Analog Devices, and Motorola DSPs.

Bioscrypt Core Sensor Interoperability:

Bioscrypt pioneered sensor interoperability to ensure flexibility across sensor offerings. Today, Bioscrypt can support interoperability between all leading sensor types, including offerings from: Atmel, AuthenTec, Delsy, DigitalPersona, Ethentica, Fidelica, Fujitsu, Infineon, Secugen, UPEK, and Veridicom. Sensor Interoperability means that templates created using any of the above sensors can be verified using any other sensor on the list, allowing the most flexibility now and in the future.

Industry Standard Interfaces:

Bioscrypt Core can be provided with support for the BioAPI (ANSI/INCITS 358-2002) or CBEFF (Common Biometric Exchange File Format - NISTIR 6529-2001) industry standards. This allows straightforward integration of Core into an application that currently supports these standards.

User Record Security

Bioscrypt's patented process for protecting user credentials can be included in Core. This functionality is combined with an encryption mechanism to provide a secure and confidential user record that can be freely transported across a network or carried on a card.

Encryption/Digital Signatures:

Bioscrypt offers functions such as data encryption or the generation of digital signatures. The inclusion of these functions within Core permits a strong connection between biometric verification and encryption techniques. For example, data can be encrypted or decrypted, or digital signatures can be created, within our solution and controlled by the biometric verification process, providing a secure implementation with powerful non-repudiation capabilities.

Bioscrypt Core Verification Library Functionality:

Bioscrypt Core has three primary functions: Enroll, Verify, and Identify.

Enrollment is the process of registering a user. The Enroll function accepts a raw image delivered directly from a sensor. The image is processed, enhanced, and compressed to create a fingerprint template. The template is returned, along with image statistics reflecting the quality of the enrollment. Subsequent verifications and identifications compare live-scan images to previously enrolled templates.

Verification is performed in order to validate a user's identity. It consists of comparing a raw candidate image to a previously enrolled template. A score is returned indicating the similarity of the candidate and template. This score can be compared to a threshold to make a yes/no decision.

Identification consists of comparing a raw candidate image to a list of previously enrolled templates. Through a series of screening processes, the algorithm narrows the list of templates to a manageable size. Those templates surviving screening are compared to the candidate and verification scores are provided. A score exceeding a pre-set threshold indicates a positive identification.

Bioscrypt Core Verification Library Specifications:
Memory Requirements
Code Space as low as 48 KB
Data Space as low as 192 KB
Template Size as low as 200 Bytes
Processing Requirements
Enroll 50 Million Instructions
Verify 80 Million Instructions
Search 200 Million Instructions

The exact requirements of Bioscrypt Core vary depending on the options chosen.

Bioscrypt Core Verification Library Technology

The Bioscrypt Core algorithm was originally developed along with Aret� Associates, a defense research company with over 25 years of experience in image processing, noise reduction, and pattern recognition associated with advanced sensor systems in use by the U.S. Department of Defense. The fundamental approach applied to developing this technology was to make the most accurate and complete comparison possible.

Methodology of the Bioscrypt Core Verification Library

Bioscrypt Core employs a pattern-based approach to fingerprint comparison. This comparison technique is performed in two fundamental blocks: Image Enhancement and Distortion Removal. In each instance that a finger is applied to a fingerprint device, the ridge pattern exhibits a different degree of distortion. The key to accurate comparison of the ridge pattern is the ability to ascertain and then remove the relative distortion between the fingerprint template and the candidate fingerprint image.

In contrast to Bioscrypt's pattern-based approach, the vast majority of fingerprint matching techniques currently employed use a minutiae-based approach. Within this approach, the fingerprint is reduced to a short list of detail points (ridge endings, bifurcations, bridges, etc). Generally, all other information from the fingerprint is eliminated. For verification, the minutiae list from the candidate is compared to the list from the template and a decision is made based on the amount of overlap.

Bioscrypt Core Verification Library Image Enhancement

Prior to enrollment or comparison, each fingerprint image is passed through a very sophisticated image enhancement routine. During this process, the image is filtered, smoothed, and conditioned to produce a high quality representation of the ridge pattern. Features such as creases, cuts, abrasions, and pores that appear inconsistently or move from place to place within the image are removed.

An illustration of the effectiveness of the Bioscrypt image enhancement algorithm is shown below.

Before Enhancement After Enhancement

Distortion Removal

Bioscrypt Core, using a unique and patented approach, aligns every ridge of the candidate image with every ridge of the template image, providing maximum use of the entire fingerprint image. Subsequent to the removal of the distortion, the ridge patterns are correlated, emphasizing areas in which the images are clean and highly complex and down weighting area where the images are noisy or bland. This technique is termed likelihood detection and is frequently utilized in mission critical U.S. Defense applications.

Minutiae algorithms frequently experience difficulty in handling large amounts of distortion. The major difficulty arises in attempting to align the minutiae points between the template and candidate. Since the information between minutiae points has previously been eliminated, it is nearly impossible for the alignment to occur.

Algorithm Accuracy

The accuracy of Bioscrypt Core has been evaluated by a variety of sensor manufacturers and other organizations. The results of these evaluations consistently show that Bioscrypt is the industry leader in algorithm accuracy.

One specific independent evaluation was FVC2002, the Second International Fingerprint Verification Competition. This competition attracted 31 entrants from around the world, including 20 algorithms from the biometrics industry and 7 algorithms from academic institutions.

To demonstrate the Bioscrypt Core versatility, Bioscrypt chose to submit two versions of Core to the competition � one focused on accuracy and the other on speed. Combined, Bioscrypt's two submissions won 19 of the 24 Gold Medals awarded and placed first and second in the official ranking.

The results for the industry entrants who chose to reveal their performance can be found below. The table shows Equal Error Rate (EER), one measure of the accuracy of an algorithm, as well as the processing time. As can be seen in the table, Bioscrypt Core is substantially more accurate than the competition.

See Fingerprint Verification Comparison Table

Additional Bioscrypt Readers:
VeriFlex
V-Pass
VeriProx
V-Smart
V-Smart iClass
V-Station
V-Cerco
VeriSoft Access Manager
MV 1200 MV Lite
Bio SDK