Active Impostor Acceptance

When an impostor submits a modified, simulated or reproduced biometric sample, intentionally attempting to relate it to another person who is an enrollee, and is incorrectly identified or verified by a biometric system as being that enrollee.

Application Developer

An individual entrusted with developing and implementing a biometric application.

Attempt

The submission of a biometric sample to a biometric system for identification or verification. A biometric system may allow more than one attempt to identify or verify.

Authentication

The process of comparing a submitted biometric sample against the biometric reference template of a single enrolee whose identity is being claimed, to determine whether it matches the enrolee's template. Contrast with 'Identification'. The preferred biometric term is 'Verification'.

Automatic ID/Auto ID

An umbrella term for any biometric system or other security technology that uses automatic means to check identity. This applies to both one-to-one verification and one-to-many identification.

Behavioural Biometric

A biometric which is characterised by a behavioural trait that is learnt and acquired over time rather than a physiological characteristic.

Biometric

A measurable, physical characteristic or personal behavioural trait used to recognise the identity, or verify the claimed identity, of an enrolee.

Biometric Application

The use to which a biometric system is put. See also 'Application Developer'.

Biometric Data

The extracted information taken from the biometric sample and used either to build a reference template or to compare against a previously created reference template.

Biometric Engine

The software element of the biometric system which processes biometric data during the stages of enrolment and capture, extraction, comparison and matching.

Biometric Identification Device

The preferred term is 'Biometric System'.

Biometric Sample

Data representing a biometric characteristic of an end-user as captured by a biometric system.

Biometric System

An automated system capable of:

capturing a biometric sample from an end user;
extracting biometric data from that sample;
comparing the biometric data with that contained in one or more reference templates;
deciding how well they match; and
indicating whether or not an identification or verification of identity has been achieved.

Biometric Taxonomy

A method of classifying biometrics. For example, San Jose State University's (SJSU) biometric taxonomy uses partitions to classify the role of biometrics within a given biometric application. Thus an application may be classified as:

Cooperative vs. Non-Cooperative User
Overt vs. Covert Biometric System
Habituated vs. Non-Habituated User
Supervised vs. Unsupervised User
Standard Environment vs. Non Standard Environment

Biometric Technology

A classification of a biometric system by the type of biometric.

Capture

The method of taking a biometric sample from the end user.

Certification

The process of testing a biometric system to ensure that it meets certain performance criteria. Systems that meet the testing criteria are said to have passed and are certified by the testing organisation.

Comparison

The process of comparing a biometric sample with a previously stored reference template or templates. See also 'One-To-Many' and 'One-To-One'.

Claim of Identity

When a biometric sample is submitted to a biometric system to verify a claimed identity.

Claimant

A person submitting a biometric sample for verification or identification whilst claiming a legitimate or false identity.

Closed-Set Identification

When an unidentified end-user is known to be enrolled in the biometric system. Opposite of 'Open-Set Identification'.

Crossover Rate

Synonym for 'Equal Error Rate'.

D Prime

A statistical measure of how well a biometric system can discriminate between different individuals. The larger the D Prime value, the better a biometric system is at discriminating between individuals.

Degrees of Freedom

The number of statistically independent features in biometric data.

Discriminant Training

A means of refining the extraction algorithm so that biometric data from different individuals are as distinct as possible.

End User

A person who interacts with a biometric system to enrol or have his/her identity checked.

End User Adaptation

The process of adjustment whereby a participant in a test becomes familiar with what is required and alters their responses accordingly.

Enrolee

A person who has a biometric reference template on file.

Enrolment

The process of collecting biometric samples from a person and the subsequent preparation and storage of biometric reference templates representing that person's identity.

Enrolment Time

The time period a person must spend to have his/her biometric reference template successfully created.

Equal Error Rate

When the decision threshold of a system is set so that the proportion of false rejections will be approximately equal to the proportion of false acceptances. A synonym is 'Crossover Rate'.

Extraction

The process of converting a captured biometric sample into biometric data so that it can be compared to a reference template.

Failure to Acquire

Failure of a biometric system to capture and extract biometric data.

Failure to Acquire Rate

The frequency of a failure to acquire.

False Acceptance

When a biometric system incorrectly identifies an individual or incorrectly verifies an impostor against a claimed identity. Also known as a Type II error.

False Acceptance Rate/FAR

The probability that a biometric system will incorrectly identify an individual or will fail to reject an impostor. Also known as the Type II error rate. It is stated as follows:
FAR = NFA / NIIA
or
FAR = NFA / NIVA
where FAR is the false acceptance rate
NFA is the number of false acceptances
NIIA is the number of impostor identification attempts
NIVA is the number of impostor verification attempts

False Match Rate

Alternative to 'False Acceptance Rate'. Used to avoid confusion in applications that reject the claimant if their biometric data matches that of an enrolee. In such applications, the concepts of acceptance and rejection are reversed, thus reversing the meaning of 'False Acceptance' and 'False Rejection'. See also 'False Non-Match Rate'.

False Non-Match Rate

Alternative to 'False Rejection Rate'. Used to avoid confusion in applications that reject the claimant if their biometric data matches that of an enrolee. In such applications, the concepts of acceptance and rejection are reversed, thus reversing the meaning of 'False Acceptance' and 'False Rejection'. See also 'False Match Rate'.

False Rejection

When a biometric system fails to identify an enrolee or fails to verify the legitimate claimed identity of an enrolee. Also known as a Type I error.

False Rejection Rate/FRR

The probability that a biometric system will fail to identify an enrolee, or verify the legitimate claimed identity of an enrolee. Also known as a Type I error rate. It is stated as follows:
FRR = NFR / NEIA
or
FRR = NFR / NEVA
where FRR is the false rejection rate
NFR is the number of false rejections
NEIA is the number of enrolee identification attempts
NEVA is the number of enrolee verification attempts

Field Test

A trial of a biometric application in 'real world' as opposed to laboratory conditions.

Goats

Biometric system end users whose pattern of activity when interfacing with the system varies beyond the specified range allowed by the system, and who consequently may be falsely rejected by the system.

Genetic Penetrance

The degree to which characteristics are passed from generation to generation.

Identification/Identify

The one-to-many process of comparing a submitted biometric sample against all of the biometric reference templates on file to determine whether it matches any of the templates and, if so, the identity of the enrolee whose template was matched. The biometric system using the one-to-many approach is seeking to find an identity amongst a database rather than verify a claimed identity. Contrast with 'Verification'.

Impostor

A person who submits a biometric sample in either an intentional or inadvertent attempt to pass him/herself off as another person who is an enrolee.

In-House Test

A test carried out entirely within the environs of the biometric developer which may or may not involve external user participation.

Live Capture

The process of capturing a biometric sample by an interaction between an end user and a biometric system.

Match/Matching

The process of comparing a biometric sample against a previously stored template and scoring the level of similarity. An accept or reject decision is then based upon whether this score exceeds the given threshold.

One-To-Many

Synonym for 'Identification'.

One-To-One

Synonym for 'Verification'.

Open-Set Identification

Identification, when it is possible that the individual is not enrolled in the biometric system. Opposite of 'Closed-Set Identification'.

Out Of Set

In open-set identification, when the individual is not enrolled in the biometric system.

Passive Impostor Acceptance

When an impostor submits his/her own biometric sample and claiming the identity of another person (either intentionally or inadvertently) he/she is incorrectly identified or verified by a biometric system. Compare with 'Active Impostor Acceptance'.

Performance Criteria

Pre-determined criteria established to evaluate the performance of the biometric system under test.

Physical/Physiological Biometric

A biometric which is characterised by a physical characteristic rather than a behavioural trait. See Part III Terms Related to Specific Biometric Techniques for 'Body Odour', 'Ear Shape', 'Face Recognition', 'Finger Geometry', 'Finger Image', 'Hand Geometry', 'Iris Recognition', 'Palm', 'Retina', 'Speaker Verification' and 'Veincheck'. Contrast with 'Behavioural Biometric'.

Receiver Operating Curves

A graph showing how the false rejection rate and false acceptance rate vary according to the threshold.

Recognition

The preferred term is 'Identification'.

Response Time

The time period required by a biometric system to return a decision on identification or verification of a biometric sample.

Template/Reference Template

Data which represents the biometric measurement of an enrolee used by a biometric system for comparison against subsequently submitted biometric samples.

Third Party Test

An objective test, independent of a biometric vendor, usually carried out entirely within a test laboratory in controlled environmental conditions.

Threshold/Decision Threshold

The acceptance or rejection of biometric data is dependent on the match score falling above or below the threshold. The threshold is adjustable so that the biometric system can be more or less strict, depending on the requirements of any given biometric application.

Throughput Rate

The number of end users that a biometric system can process within a stated time interval.

Type I Error

See 'False Rejection'.

Type II Error

See 'False Acceptance'.

User

The client to any biometric vendor. The user must be differentiated from the end user and is responsible for managing and implementing the biometric application rather than actually interacting with the biometric system.

Validation

The process of demonstrating that the system under consideration meets in all respects the specification of that system.

Verification/Verify

Zero Effort Forgery

An arbitrary attack on a specific enrolee identity in which the impostor masquerades as the claimed enrolee using his or her own biometric sample.

Terms Related To Specific Biometric Techniques

Terms relating to specific biometric technologies and techniques are grouped below.

1. AFIS (Automated Fingerprint Identification System)

A highly specialised biometric system that compares a single finger image with a database of finger images. AFIS is predominantly used for law enforcement, but is also being put to use in civil applications. For law enforcement, finger images are collected from crime scenes, known as latents, or are taken from criminal suspects when they are arrested. In civilian applications, finger images may be captured by placing a finger on a scanner or by electronically scanning inked impressions on paper. See also Part III Biometric Specific Terms number 6, Finger Image.

Binning: A specialised technique used by some AFIS vendors. Binning is the process of classifying finger images according to finger image patterns. This predominantly takes place in law enforcement applications. Here finger images are categorised by characteristics such as arches, loops and whorls and held in smaller, separate databases (or bins) according to their category. Searches can be made against particular bins, thus speeding up the response time and accuracy of the AFIS search.

Booking: The process of capturing inked finger images on paper, for subsequent processing by an AFIS.

Filtering: A specialised technique used by some AFIS vendors. Filtering is the process of classifying finger images according to data which is unrelated to the finger image itself. This may involve filtering by sex, age, hair colour or other distinguishing factors.

Latent: An impression of a finger image collected from a crime scene.

2. Body Odour

A physical biometric that analyses the unique chemical pattern made up by human body smell.

Volatiles: The chemical breakdown of body odour.

3. DNA

DNA is a unique, measurable human characteristic. However, current DNA technology is not automatic and cannot currently rank alongside other biometric technologies.

4. Ear Shape

A lesser-known physical biometric that is characterised by the shape of the outer ear, lobes and bone structure.

5. Face Recognition

A physical biometric that analyses facial features.

Eigenface: A method of representing a human face as a linear deviation from a mean or average face.

Eigenhead: The three dimensional version of Eigenface that also analyses the shape of the head.

Face Monitoring: A biometric application of face recognition technology where the biometric system monitors the attendance of an end user at a desktop.

Facial Thermogram: A specialised face recognition technique that senses heat in the face caused by the flow of blood under the skin.

6. Finger Image

A physical biometric which looks at the patterns found in the tip of the finger.

Auto-correlation: A proprietary fingerscanning technique. Two identical finger images are overlaid in the auto-correlation process, so that light and dark areas, known as Moir� fringes, are created.

Bifurcation: A branch made by more than one finger image ridge.

Capacitance: A finger image capture technique that senses an electrical charge, from the contact of ridges, when a finger is placed on the surface of a sensor.

DPI (Dots Per Inch): A measurement of resolution for finger image biometrics.

Fingerprint/Fingerprinting: The preferred terms are now 'Finger Image' and 'Fingerscanning'.

Fingerscanning: The process of finger image capture.

Live Scan: The term live scan is typically used in conjunction with finger image technology. Synonym for 'Live Capture'. See Part I General Biometric Terms.

Minutiae: Small details found in finger images such as ridge endings or bifurcations.

Optical: A finger image capture technique that uses a light source, a prism and a platen to capture finger images.

Platen: The surface on which a finger is placed during optical finger image capture.

Ridge: The raised markings found across the fingertip. See also 'Valley'.

Ridge Ending: The point at which a finger image ridge ends.

Ultrasound: A technique for finger image capture that uses acoustic waves to measure the density of a finger image pattern.

Thermal: A finger image capture technique that uses a sensor to sense heat from the finger and thus capture a finger image pattern.

Valley: The corresponding marks found on either side of a finger image ridge.

7. Finger Geometry

A physical biometric that analyses the shape and dimensions of one or more fingers.

8. Hand Geometry/Hand Recognition

A physical biometric that involves analysing and measuring the shape of the hand.

9. Iris Recognition

A physical biometric that analyses iris features, found in the coloured ring of tissue that surrounds the pupil.

Iris Features: A number of features can be found in the iris. These are named corona, crypts, filaments, freckles, pits, radial furrows and striations.

IrisCode: The biometric data that is generated for each live iris presented. The code is a mathematical representation of the features of the iris. See also 'Biometric Data'.

10. Keystroke Dynamics

A behavioural biometric under development that analyses typing rhythm when an end user types onto a keyboard.

11. Palm

A physical biometric that analyses the palm of the hand. Typically this will involve an analysis of minutiae data.

12. Retina

A physical biometric that analyses the layer of blood vessels situated at the back of the eye.

13. Signature Verification

A behavioural biometric that analyses the way an end user signs his/her name. The signing features such as speed, velocity and pressure exerted by a hand holding a pen are as important as the static shape of the finished signature.

Acoustic Emission: A proprietary technique used in signature verification. As a user writes on a paper surface, the movement of the pen tip over the paper fibres generates acoustic emissions that are transmitted in the form of stress waves within the material of a writing block beneath the document being signed. The structure-borne elastic waves behave in materials in a similar way to sound waves in air and can be detected by a sensor attached to the writing block.

DSV (Dynamic Signature Verification): Synonym for 'Signature Verification'.

14. Speaker verification

A part physical, part behavioural biometric that analyses patterns in speech.

Fixed-Text System: The preferred term is 'Text-Dependent System'.

Free-Text System.: The preferred term is 'Text-Independent System'.

Speaker-Dependent: A term sometimes used by speaker verification vendors to emphasise the fact their technology is designed to distinguish among voices.

Speaker Separation: A technology that separates overlapping voices from each other and other background noises.

Speech Recognition: This is not a biometric and should not be confused with speaker verification. Speech recognition involves recognising words as they are spoken and does not identify the speaker.

SVAPI (Speaker Verification Application Program Interface): A biometric API for speaker verification systems.

Text-Dependent System: A system that requires a speaker to say a specific set of numbers or words.

Text-Independent System: A system that creates voiceprints from unconstrained speech and does not require a speaker to say a specific set of numbers or words.

Text-Prompted System: A speaker verification system that prompts the speaker to say randomly ordered numbers or words. The term 'Challenge-Response' is also used in a similar way to define text prompting.

Voice Verification: The preferred term is 'Speaker Verification'.

Voice Print/Voiceprint: A representation of the acoustic information found in the voice of a speaker.

15. Veincheck/Vein Tree

A physical biometric under development that analyses the pattern of veins in the back of the hand.

BAPI Glossary

The following is an alphabetical glossary of terms used in relation to the Biometric Application Programming Interface (BAPI):

BAPI Device Module Interface (BDMI)
This is the interface between BAPI and the physical biometric device. The device manufacturer provides a BDM, which is an instance of BDMI, to support BAPI on a given operating platform for their device.

BAPI Device Module (BDM)
This is essentially a device driver provided by the device manufacturer that maps a particular device’s capabilities into the functionality provided by BAPI and defined by BDMI.

Biometric Application Programming Interface (BAPI)
This is an API that allows the programmer to develop applications for a broad range of virtual biometric devices (VBDs) without knowing the specific capabilities of the device. The API is comprised of three distinct levels of functionality from high device abstraction to low (device specific) abstraction.

biometric device
A physical device that is typically attached to a microcomputer (in our paradigm) that can obtain and process distinctive human characteristic data such as fingerprint scanners, retina pattern analyzers, voice analyzers, etc.

biometric element
The physical portion of a biometric device that is used to actively or passively acquire biometrics data from a biometrics sampling source.

biometric sample/data
The information obtained from a biometric device that contains the encoded information that is the distinctive human characteristic data such as a finger print, retina pattern, voice prints, etc.

biometric sampling source
The target entity for which the biometric device is designed to sample, scan, read, etc.

channel
A channel is the method by which a component processes data, whether that process is creation, transformation or comparison. Each component type is expected to contain one or more standard channels. In addition, any number of extended channels may be defined in order to fully enumerate the capabilities of a particular biometrics device.

comparison
The act of matching sampled biometric data against another set of data for verifying and/or identifying an individual. Comparison is always done between comparison data and template data. Comparison returns a score that indicates the degree to which comparison data and template data match.

Comparison data
This is the data sampled from a biometric sampling source and is typically used for comparison to stored template data.

component
A component is essentially a logical classification of one particular step in the biometrics authentication/identification process. There are five categories of components: Samplers, Filters, Engines, Storage, and OEM defined components.

control
Controls can affect the way data is processed by the channels, or supply BAPI functions with important information regarding a channel's and/or device's status.

S-template
Functionally equivalent to "comparison data" (described above). Stands for comparison "sample – template."

T-template
Functionally equivalent to "template data" (described below). Stands for comparison "target – template."

engine component
An engine component provides the processing functionality in order to verify or identify an individual. An ENGINE component drives a particular process.

event
An event is the occurrence of an incident such as a mouse click, key press, etc.

event driven
Indicates that a process is controlled and/or communicates using events. These events are used as signals to inform any or all processes of thread, hardware, or software status and other information that is needed by a process to continue, pause, or terminate execution, etc.

filter component
This component functions to reduce or optimize raw biometric data to be later be used in comparison and/or verification functions.

Hardware Abstraction Layer (HAL)
This is the logical portion of a system that separates the OS from the modules of the system that make use of any OS provided functionality.

High Level BAPI (HBAPI; Level 3)
High level BAPI is intended for use in writing applications that are expected to utilize an arbitrarily selected BAPI compliant physical biometric device. At this level, the applications programmer must use the standard VBD programming model.

identify
This is a one-to-many comparison of sampled comparison data to the template data stored in a template database. In this case, it is not necessary for the user to identify himself to the system before beginning the identification process. Identification is often slower than verification (because of the need to search a large database), and many biometric systems cannot perform this function. This can be the same as verify, but may often have an optimized and separate processing mechanism associated with it on a biometric device.

Low Level BAPI (LBAPI; Level 1)
The lowest level of BAPI allows the applications programmer to utilize the special features of a biometric device from a known manufacturer. This level allows for complete control of a specific biometric device.

Middle Level BAPI (MBAPI; Level 2)
The mid level of BAPI is used when the programmer knows the categorical type of biometric device that will be used. This level is best used when the category is known but the physical device is still arbitrary.

multithreaded
Denotes the capability to execute multiple executables or portions of an executable simultaneously. BAPI is multithreaded and supports multithreaded BAPI applications by ensuring that each application executes within its own execution context within BAPI. BAPI manages this context as well as resource and device access and contention.

profile data
General information regarding an individual that can be stored in the user's database within VBD.

raw data
This is the initial biometric data obtained from a sampling source before any reduction, processing, or optimizing occurs.

sampling
The act of acquiring biometric data from a sampling source.

score
The numerical result of a comparison function. It indicates to what degree the sampled biometric data matches the stored template data for an individual.

sensor
The mechanism on a biometric device for checking for the presence of a biometric sampling source ready to be sampled.

status report
The means by which a biometric device can report its operational status. LED’s and LCD displays on the physical devices are examples of status indicators.

S-Process
This is the process of sampling biometric data from a biometric sampling source so that it can be reduced into template data and then used directly for comparison functionality.

storage component
Storage components provide access to nonvolatile memory areas within the VBD model.

template data
This is the result of reducing or optimizing the raw data obtained during a sampling process (T–Process) for use in identifying or verifying an individual. In most cases, the idea behind a template is to reduce the size of the raw data into the smallest size possible while still retaining the data’s inherent uniqueness.

T-Process
This is the process of obtaining biometric data from a biometric sampling source so that it can be reduced into template data and then typically stored for use in future comparison functions.

Users Database
A database of USER records internally maintained by the VBD.

USER record
A USER is a database record containing information about an individual and their template and or profile data.

Virtual Biometric Device (VBD)
Provides an abstraction layer between the BAPI application and a physical biometric device which contains the common core functionality and components which are shared by all biometric devices. By targeting the VBD model, a BAPI programmer can write an application, which targets all BAPI compliant biometric devices.

verify
This is a one-to-one comparison of stored template data to sampled comparison data. This can be the same as identify, but may often have an optimized and separate processing mechanism associated with it on a biometric device. The verification process simply certifies that the user is who he says he is.