Glossary of Biometric Terms

AFIS (Automated Fingerprint Identification System): A highly specialized 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 Finger Image.

Algorithm: A sequence of instructions that tell a biometric system how to solve a particular problem. An algorithm will have a finite number of steps and is typically used by the biometric engine to compute whether a biometric sample and template are a match. See also Artificial Neural Network.

API (Application Program Interface): A set of services or instructions used to standardize an application. An API is computer code used by an application developer. Any biometric system that is compatible with the API can be added or interchanged by the application developer. APIs are often described by the degree to which they are high level or low level. High level means that the interface is close to the application and low level means that the interface is close to the device.

ASIC (Application Specific Integrated Circuit): An integrated circuit (silicon chip) that is specially produced for a biometric system to improve performance.

Authentication: Alternative term for 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.

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

Biometric: A measurable, physical characteristic or personal behavioral trait used to recognize the identity, or verify the claimed identity, of an enrollee.

Biometric Data: The information extracted from the biometric sample and used either to build a reference template (template data) or to compare against a previously created reference template (comparison data).

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 Sample: Raw data representing a biometric characteristic of an end-user as captured by a biometric system (for example the image of a fingerprint).

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.

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

CCD (Charge-Coupled Device): A CCD is a semiconductor device that records images electronically.

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 organization.

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.

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

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 Error Rate: Synonym for Equal Error Rate.

Database: Any storage of biometric templates and related end user information. Even if only one biometric template or record is stored, the database will simply be a database of one. Generally speaking, however, a database will contain a number of biometric records.

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.

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

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

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

Encryption: The act of converting biometric data into a code so that people will be unable to read it. A key or a password is used to decrypt (decode) the encrypted biometric data.

Enrollee: 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: The error rate occurring 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.

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 (comparison data).

Failure to Acquire Rate: The frequency of a failure to acquire.

Failure to Enroll: Failure of the biometric system to form a proper enrolment template for an end-user. The failure may be due to failure to capture the biometric sample or failure to extract template data (of sufficient quality).

Failure to Enroll Rate: The proportion of the population of end-users failing to complete enrolment

False Acceptance: When a biometric system incorrectly identifies an individual or incorrectly verifies an impostor against a claimed identity.

False Acceptance Rate/FAR: The probability that a biometric system will incorrectly identify an individual or will fail to reject an impostor. The rate given normally assumes passive impostor attempts. The False Accept Rate may be estimated as
                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 enrollee. 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 enrollee. 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 enrollee or fails to verify the legitimate claimed identity of an enrollee.

False Rejection Rate/FRR: The probability that a biometric system will fail to identify an enrollee, or verify the legitimate claimed identity of an enrollee. The False Rejection Rate may be estimated 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 enrollee identification attempts
                NEVA is the number of enrollee verification attempts
This estimate assumes that the enrollee identification/verification attempts are representative of those for the whole population of end-users. The False Rejection Rate normally excludes Failure to Acquire errors.

Filtering: The process of classifying biometric data according to information that is unrelated to the biometric data itself. This may involve filtering by sex, age, hair color or other distinguishing factors, and including this information in an end users database record. This term is particularly used in conjunction with Automated Fingerprint Identification Systems. See Part 2, AFIS, Filtering.

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

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

Finger scanning: The process of finger image capture

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 enrollee 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 enrollee.

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

Live Scan: The term live scan is typically used in conjunction with finger image technology. Synonym for Live Capture.

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.

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

Multiple Biometric: A biometric system that includes more than one biometric system or biometric technology.

One-to-a-Few: A hybrid of one-to-many identification and one-to-one verification. Typically the one-to-a-few process involves comparing a submitted biometric sample against a small number of biometric reference templates on file.

One-to-Many: Synonym for Identification.

One-to-One: Synonym for Verification.

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

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

PIN (Personal Identification Number): A security method whereby a (usually) four digit number is entered by an individual to gain access to a particular system or area.

Population: The set of end-users for the application.

Receiver Operating Curves (ROC): A graph showing how the false rejection rate and false acceptance rate vary according to the threshold.

Recognition: The preferred term is Identification.

Record: The template and other information about the end-user (e.g. access permissions)

Response Time: The time period for a biometric system to return a decision on identification or verification of a biometric sample.

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

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

RF: A unique type of finger image capture that uses RF signals to capture the finger image under the outer layer of the skin, to the live layer below.

Score: The level of similarity from comparing a biometric sample against a previously stored template.

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

Template Ageing: The degree to which biometric data evolves and changes over time, and the process by which templates account for this change.

Template Size: The amount of computer memory taken up by the biometric data.

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

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.

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

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.

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

Verification/Verify: The process of comparing a submitted biometric sample against the biometric reference template of a single enrollee whose identity is being claimed, to determine whether it matches the enrollees template. Contrast with Identification.