ISO/IEC 2382-37:2017

INTERNATIONAL ISO/IEC
STANDARD 2382-37
Second edition
2017-02
Information technology —
Vocabulary —
Part 37:
Biometrics
Technologies de l’information — Vocabulaire —
Partie 37: Biométrie
Reference number
ISO/IEC 2382-37:2017(E)
©
ISO/IEC 2017

---------------------- Page: 1 ----------------------
ISO/IEC 2382-37:2017(E)

COPYRIGHT PROTECTED DOCUMENT
© ISO/IEC 2017, Published in Switzerland
All rights reserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any form
or by any means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior
written permission. Permission can be requested from either ISO at the address below or ISO’s member body in the country of
the requester.
ISO copyright office
Ch. de Blandonnet 8 • CP 401
CH-1214 Vernier, Geneva, Switzerland
Tel. +41 22 749 01 11
Fax +41 22 749 09 47
copyright@iso.org
www.iso.org
ii © ISO/IEC 2017 – All rights reserved

---------------------- Page: 2 ----------------------
ISO/IEC 2382-37:2017(E)

Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
3.1 General concept terms . . 1
3.2 Biometric system terms . 2
3.3 Terms for data in biometric systems . 3
3.4 Device terms. 9
3.5 Functioning terms . 9
3.6 Interacting terms.12
3.7 Personnel terms .16
3.8 Application terms .18
3.9 Performance terms .19
Bibliography .23
Index 23
© ISO/IEC 2017 – All rights reserved iii

---------------------- Page: 3 ----------------------
ISO/IEC 2382-37:2017(E)

Foreword
ISO (the International Organization for Standardization) and IEC (the International Electrotechnical
Commission) form the specialized system for worldwide standardization. National bodies that are
members of ISO and IEC participate in the development of International standards through technical
committees established by the respective organization to deal with particular fields of technical
activity. ISO and IEC technical committees collaborate in fields of mutual interest. Other international
organizations, governmental and non-governmental, in liaison with ISO and IEC, also take part in the
work. In the field of information technology, ISO and IEC have established a joint technical committee,
ISO/IEC JTC 1.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www .iso .org/ directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www .iso .org/ patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation on the meaning of ISO specific terms and expressions related to conformity assessment,
as well as information about ISO’s adherence to the World Trade Organization (WTO) principles in the
Technical Barriers to Trade (TBT) see the following URL: www . i so .org/ iso/ foreword .html.
The committee responsible for this document is ISO/IEC JTC 1, Information technology, Subcommittee
SC 37, Biometrics.
This second edition cancels and replaces the first edition (ISO/IEC 2382-37:2012). Minor changes have
been made to some of the terms published in the 2012 edition and 41 new terms have been added.
iv © ISO/IEC 2017 – All rights reserved

---------------------- Page: 4 ----------------------
ISO/IEC 2382-37:2017(E)

Introduction
The main purpose of this document is to provide a systematic description of the concepts in the subject
field of biometrics and to clarify the use of the terms in this subject field. The subject field of biometrics
is broken down into subfields.
This document is addressed to biometrics standardizers and to users of these standards.
Terms defined in this document are to be understood in the subject field of biometrics. When terms
exist in various subject fields, the current subject field may be indicated in angle brackets.
Words that are bolded are defined in this document. Words that are not bolded are to be understood
in their natural language sense. The authority for natural language use of terms in this document is the
Concise Oxford English Dictionary, Thumb Index Edition (tenth edition, revised, 2002).
EXAMPLE
candidate
biometric reference identifier (3.3.19) of a biometric reference (3.3.16) in the biometric
reference database (3.3.17) determined to be similar to the biometric probe (3.3.14)
candidate
a person who applies for a job or is nominated for election
NOTE When using terms defined with a qualifier (for example, “biometric xxx”), it is normal to include the
qualifier on the first occurrence of the term in every paragraph, but to omit it on subsequent occurrences of that
term within the same paragraph. In broader contexts, where the qualifier (in this case, ‘biometric’) is clearly
understood, then the qualifier may be omitted completely.
The terms in this document are listed in a systematic order under a number of general headings.
The layout follows the directions given in ISO 10241-1. Thus, the elements of an entry appear in the
following order:
— Entry number (mandatory);
— Preferred term(s) (mandatory);
— Admitted term(s) (mandatory);
— Deprecated term(s);
— Definition;
— Example(s);
— Note(s).
© ISO/IEC 2017 – All rights reserved v

---------------------- Page: 5 ----------------------
INTERNATIONAL STANDARD ISO/IEC 2382-37:2017(E)
Information technology — Vocabulary —
Part 37:
Biometrics
1 Scope
This document establishes a systematic description of the concepts in the field of biometrics pertaining
to recognition of human beings and reconciles variant terms in use in pre-existing biometric standards
against the preferred terms, thereby clarifying the use of terms in this field.
Excluded from the scope of this document are concepts (represented by terms) from information
technology, pattern recognition, biology, mathematics, etc. Biometrics uses such fields of knowledge as
a basis.
In principle, mode specific terms are outside of scope of this document.
Words that are bolded are defined in this document. Words that are not bolded are understood in their
natural language sense. The authority for natural language use of terms in this document is the Concise
Oxford English Dictionary, Thumb Index Edition (tenth edition, revised, 2002). Words used in their
natural language sense are considered out-of-scope for further definition in this document.
2 Normative references
There are no normative references in this document.
3 Terms and definitions
3.1 General concept terms
3.1.1
biometric (adjective)
of or having to do with biometrics (3.1.3)
EXAMPLE 1 Incorrect usage #1: ICAO resolved that face is the biometric most suited to the practicalities of
travel documents.
EXAMPLE 2 Correct usage #1: ICAO resolved that face recognition is the biometric mode (3.2.5) most suited to
the practicalities of travel documents.
EXAMPLE 3 Incorrect usage #2: The biometric recorded in my passport is a facial image.
EXAMPLE 4 Correct usage #2: The biometric characteristic (3.1.2) recorded in my passport is a facial image.
Note 1 to entry: The use of biometric as a noun, to mean for example, biometric characteristic (3.1.2), is
deprecated.
Note 2 to entry: Since the late 19th century, the designations ‘biometrics’ and ‘biometry’ have been used with
the general meaning of counting, measuring and statistical analysis of any kind of data in the biological sciences
including the relevant medical sciences.
© ISO/IEC 2017 – All rights reserved 1

---------------------- Page: 6 ----------------------
ISO/IEC 2382-37:2017(E)

3.1.2
biometric characteristic
DEPRECATED: biometric (noun)
biological and behavioural characteristic of an individual from which distinguishing, repeatable
biometric features (3.3.11) can be extracted for the purpose of biometric recognition (3.1.3)
EXAMPLE Examples of biometric characteristics are: Galton ridge structure, face topography, facial skin
texture, hand topography, finger topography, iris structure, vein structure of the hand, ridge structure of the
palm, retinal pattern, handwritten signature dynamics, etc.
3.1.3
biometric recognition
biometrics
automated recognition of individuals based on their biological and behavioural characteristics
Note 1 to entry: In the field of biometrics (as defined in this document), “Individual” is restricted in scope to
refer only to humans.
Note 2 to entry: The general meaning of biometrics encompasses counting, measuring and statistical analysis of
any kind of data in the biological sciences including the relevant medical sciences.
Note 3 to entry: Biometric recognition encompasses biometric verification (3.8.3) and biometric identification
(3.8.2).
Note 4 to entry: Automated recognition implies that a machine based system is used for the recognition either for
the full process or assisted by a human being.
Note 5 to entry: Behavioural and biological characteristics cannot be completely separated which is why
the definition uses ‘and’ instead of ‘and/or’. For example, a fingerprint image results from the biological
characteristics of the finger ridge patterns and the behavioural act of presenting the finger.
Note 6 to entry: Use of ‘authentication’ as a synonym for “biometric verification (3.8.3) or biometric identification
(3.8.2)” is deprecated; the term biometric recognition is preferred.
3.2 Biometric system terms
3.2.1
biometric capture subsystem
biometric capture devices (3.4.1) and any sub-processes required to execute a biometric capture
process (3.5.2)
Note 1 to entry: In some systems, converting a signal from a biometric characteristic (3.1.2) to a captured biometric
sample (3.3.25) may include multiple components such as a camera, photographic paper, printer, digital scanner,
ink and paper.
Note 2 to entry: A biometric capture subsystem can consist of only a single biometric capture device (3.4.1).
3.2.2
biometric identification system
system that aims to perform biometric identification (3.8.2)
3.2.3
biometric system
system for the purpose of the biometric recognition (3.1.3) of individuals based on their behavioural and
biological characteristics
Note 1 to entry: A biometric system will contain both biometric (3.1.1) and non-biometric components.
3.2.4
biometric verification system
system that aims to perform biometric verification (3.8.3)
2 © ISO/IEC 2017 – All rights reserved

---------------------- Page: 7 ----------------------
ISO/IEC 2382-37:2017(E)

3.2.5
mode
DEPRECATED: biometric (noun)
combination of a biometric characteristic (3.1.2) type, a sensor type and a processing method
Note 1 to entry: The processing algorithm may contain multiple methods, details of which may not be externally
apparent. Thus a biometric system (3.2.3) is considered as using one processing method, until it is otherwise
specified.
Note 2 to entry: Determining what constitutes a single type of sensor, processing method or biometric
characteristic (3.1.2) will depend on convention. For example, current convention is that images of ridge patterns
from both thumbs and fingers represent a single biometric characteristic (3.1.2) type, i.e. fingerprints. With
respect to sensors, infrared and optical bandwidth sensors are considered different types, but optical bandwidth
sensors are considered a single type despite imaging red, green and blue bandwidths.
3.2.6
multi-modal
multiple in at least 2 out of 3 constituents of a mode (3.2.5) in a single biometric system (3.2.3)
Note 1 to entry: Multiple implies difference in type.
3.2.7
system participation ratio
proportion of individuals eligible to use the system who do use the system
Note 1 to entry: Enrolled individuals are a subset of eligible individuals.
3.3 Terms for data in biometric systems
3.3.1
anonymized biometric data record
biometric data record (3.3.8) purposely disassociated from individual metadata
Note 1 to entry: The biometric data (3.3.6) within the biometric data record (3.3.8) ultimately remains attributable
to an individual.
3.3.2
biometric application database
database of biometric data (3.3.6) and associated metadata developed from and supporting the
operation of a biometric (3.1.1) application
Note 1 to entry: The metadata may include transaction history; authorizations (e.g. age) of biometric data subject
(3.7.5); and archived biometric data (3.3.6).
Note 2 to entry: The term application includes the policies that govern the operation of the system and evidence
of that operation.
3.3.3
biometric application decision
decision to perform an action at the application level based on the results of a biometric (3.1.1) process
Note 1 to entry: The application decision may include more than a comparison (3.5.7) process. For example, a
biometric capture process (3.5.2) may show that there are no characteristics to capture and a decision can be
made on this before any biometric characteristics (3.1.2) are compared.
Note 2 to entry: Biometric application decisions can be made on the basis of complex policies involving both
biometric (3.1.3) and non-biometric data.
3.3.4
biometric candidate
biometric reference identifier (3.3.19) of a biometric reference (3.3.16) in the biometric reference database
(3.3.17) determined to be sufficiently similar to the biometric probe (3.3.14) to warrant further analysis
© ISO/IEC 2017 – All rights reserved 3

---------------------- Page: 8 ----------------------
ISO/IEC 2382-37:2017(E)

3.3.5
biometric candidate list
set of zero, one or more biometric candidates (3.3.4) that may be intermediate or final
Note 1 to entry: Intermediate biometric candidate lists may be produced by systems that use multi-pass
biometric identification (3.8.2).
Note 2 to entry: Biometric candidate lists may or may not be ordered.
3.3.6
biometric data
biometric sample (3.3.21) or aggregation of biometric samples (3.3.21) at any stage of processing, e.g.
biometric reference (3.3.16), biometric probe (3.3.14), biometric feature (3.3.11) or biometric property
(3.3.15)
Note 1 to entry: Biometric data need not be attributable to a specific individual, e.g. Universal Background Models.
3.3.7
biometric database
database of biometric data record(s) (3.3.8)
3.3.8
biometric data record
data record containing biometric data (3.3.6)
Note 1 to entry: A biometric data record may include non-biometric data.
3.3.9
biometric enrolment database
database of biometric enrolment data record(s) (3.3.10)
Note 1 to entry: A database of biometric data (3.3.6) not attributable to biometric data subjects (3.7.5) is a
biometric database (3.3.7), but not a biometric enrolment database, e.g. a database utilised in the training of a
Universal Background Model.
Note 2 to entry: The biometric enrolment database may or may not contain the biometric reference database
(3.3.17). Separation of the databases may be required due to security, privacy, legislation, architecture,
performance, etc.
Note 3 to entry: A single biometric reference (3.3.16) (e.g. a fingerprint on a storage card) may be considered as a
biometric enrolment database in some transactions.
3.3.10
biometric enrolment data record
data record attributed to a biometric data subject (3.7.5), containing non-biometric data and associated
with biometric reference identifier(s) (3.3.19)
Note 1 to entry: Data can be updated after enrolment.
Note 2 to entry: The biometric enrolment data record will either contain biometric reference data record(s)
(3.3.18) or pointer(s) to biometric reference data record(s) (3.3.18).
Note 3 to entry: The associated biometric reference (3.3.16) may be null (for example, biometric enrolee (3.7.6)
lacks the biometric characteristic (3.1.2) or a biometric capture process (3.5.2) is pending).
3.3.11
biometric feature
numbers or labels extracted from biometric samples (3.3.21) and used for comparison (3.5.7)
Note 1 to entry: Biometric features are the output of a completed biometric feature extraction (3.5.4).
Note 2 to entry: The use of this term should be consistent with its use by the pattern recognition and mathematics
communities.
4 © ISO/IEC 2017 – All rights reserved

---------------------- Page: 9 ----------------------
ISO/IEC 2382-37:2017(E)

Note 3 to entry: A biometric feature set can also be considered a processed biometric sample (3.3.21).
Note 4 to entry: Biometric features may be extracted from an intermediate biometric sample (3.3.30).
Note 5 to entry: Filters applied to biometric samples (3.3.21) are not themselves biometric features, however
the output of the filter applied to these samples may be. Therefore, for example, eigenfaces are not biometric
features.
3.3.12
biometric identification decision
comparison decision (3.3.26) as to whether a biometric reference(s) (3.3.16) of a particular biometric
data subject (3.7.5) is in a biometric reference database (3.3.17)
Note 1 to entry: Return of a biometric candidate list (3.3.5) is not considered a biometric identification decision.
Note 2 to entry: A positive biometric identification (3.8.2) process is inferred from the output of a biometric
reference identifier (3.3.19).
3.3.13
biometric model
stored function generated from biometric data (3.3.6)
EXAMPLE Examples of biometric models could be a Hidden Markov Model, Gaussian Mixture Model or an
Artificial Neural Network.
Note 1 to entry: In most occasions, the biometric model is a stored function which is dependent on the biometric
data subject (3.7.5).
Note 2 to entry: The function may be determined through training.
Note 3 to entry: A biometric model may involve intermediate processing similar to biometric feature extraction
(3.5.4).
3.3.14
biometric probe
biometric query
biometric sample (3.3.21) or biometric feature (3.3.11) set input to an algorithm for biometric comparison
(3.5.7) to a biometric reference(s) (3.3.16)
Note 1 to entry: In some comparisons (3.5.7), a biometric reference (3.3.16) might be used as the subject of the
comparison with other biometric references (3.3.16) or incoming biometric samples (3.3.21) used as the objects of
the comparisons (3.5.7). For example, in a duplicate enrolment check, a biometric reference (3.3.16) will be used as
the subject for comparisons (3.5.7) against all other biometric references (3.3.16) in the database.
Note 2 to entry: Typically in a biometric comparison (3.5.7) process, incoming biometric samples (3.3.21) serve as
the subject of comparisons (3.5.7) against objects stored as biometric references (3.3.16) in a database.
3.3.15
biometric property
descriptive attributes of the biometric data subject (3.7.5) estimated or derived from the biometric
sample (3.3.21) by automated means
EXAMPLE Fingerprints can be classified by the biometric properties of ridge-flow, i.e. arch, whorl, and
loop types. Estimates of age or gender from face recognition would also be biometric properties.
3.3.16
biometric reference
one or more stored biometric samples (3.3.21), biometric templates (3.3.22) or biometric models (3.3.13)
attributed to a biometric data subject (3.7.5) and used as the object of biometric comparison (3.5.7)
EXAMPLE Face image stored digitally on a passport, fingerprint minutiae template on a National ID card or
Gaussian Mixture Model for speaker recognition, in a database.
© ISO/IEC 2017 – All rights reserved 5

---------------------- Page: 10 ----------------------
ISO/IEC 2382-37:2017(E)

Note 1 to entry: A biometric reference may be created with implicit or explicit use of auxiliary data, such as
Universal Background Models.
Note 2 to entry: The subject/object labelling in a comparison (3.5.7) might be arbitrary. In some comparisons
(3.5.7), a biometric reference might be used as the subject of the comparison with other biometric references
or incoming samples and input to an algorithm for biometric comparison (3.5.7). For example, in a duplicate
enrolment check a biometric reference will be used as the subject for comparison against all other biometric
references in the database.
3.3.17
biometric reference database
database of biometric reference data records (3.3.18)
Note 1 to entry: The biometric reference database may be a subset of the biometric enrolment database (3.3.9),
or it may be a separate database. Separation of the databases may be required due to security, privacy, legislation,
architecture, performance, etc.
3.3.18
biometric reference data record
indexed data record containing biometric reference(s) (3.3.16)
Note 1 to entry: There may not be a one-to-one correspondence between biometric reference data records
and biometric data subjects (3.7.5), e.g. a single biometric data subject (3.7.5) might have several reference data
records and in some applications, a single biometric reference data record might be associated with multiple
enrolments of a biometric data subject (3.7.5).
3.3.19
biometric reference identifier
pointer to a biometric reference data record (3.3.18) in the biometric reference database (3.3.17)
3.3.20
biometric representation
biometric sample (3.3.21) or biometric feature (3.3.11) set
Note 1 to entry: This term is used in ISO/IEC 19794 biometric data interchange format standards for labelling a
sub-record in a biometric data record (3.3.8).
3.3.21
biometric sample
analog or digital representation of biometric characteristics (3.1.2) prior to biometric feature
extraction (3.5.4)
EXAMPLE A record containing the image of a finger is a biometric sample.
3.3.22
biometric template
reference biometric feature set
set of stored biometric features (3.3.11) comparable directly to probe biometric features (3.3.11)
EXAMPLE A record containing a set of finger minutiae is a biometric template.
Note 1 to entry: A biometric reference (3.3.16) consisting of an image, or other captured biometric sample (3.3.25),
in its original, enhanced or compressed form, is not a biometric template.
Note 2 to entry: The biometric features (3.3.11) are not considered to be a biometric template unless they are
stored for reference.
3.3.23
biometric verification decision
comparison decision (3.3.26) determining the validity of a biometric claim (3.6.4) in a verification
transaction (3.6.21)
6 © ISO/IEC 2017 – All rights reserved

---------------------- Page: 11 ----------------------
ISO/IEC 2382-37:2017(E)

3.3.24
biometric candidate score
comparison score (3.3.27) for a biometric candidate (3.3.4)
3.3.25
captured biometric sample
DEPRECATED: raw biometric sample
biometric sample (3.3.21) resulting from a biometric capture process (3.5.2)
3.3.26
comparison decision
determination of whether the biometric probe(s) (3.3.14) and biometric reference(s) (3.3.16) have the
same biometric (3.1.1) source, based on a comparison score(s) (3.3.27), a decision policy(ies) including a
threshold (3.3.36), and possibly other inputs
Note 1 to entry: A match (3.3.31) is a positive comparison decision. A non-match (3.3.33) is a negative
comparison decision. A decision of “undetermined” may sometimes be given.
3.3.27
comparison score
DEPRECATED: matching score
numerical value (or set of values) resulting from a comparison (3.5.7)
Note 1 to entry: Higher does not necessarily mean more similar.
3.3.28
dissimilarity score
distance score
comparison score (3.3.27) that decreases with similarity
Note 1 to entry: Unlike a distance score, a dissimilarity score does not have to meet the mathematical definition
of a metric on a set.
3.3.29
fraudulent biometric enrolment data record
biometric enrolment data record (3.3.10) created or modified for the purpose of supporting wrongful or
criminal activity
Note 1 to entry: Records that are inadvertently erroneous or created for test purposes are not considered
fraudulent.
3.3.30
intermediate biometric sample
biometric sample (3.3.21) resulting from intermediate biometric sample processing (3.5.9)
EXAMPLE Biometric samples (3.3.21) that have been cropped, down-sampled, compressed, or enhanced are
examples of intermediate biometric samples.
3.3.31
match (noun)
comparison decision (3.3.26) stating that the biometric probe(s) (3.3.14) and the biometric reference
(3.3.16) are from the same source
Note 1 to entry: Historically, the word match has been used as a verb to indicate the act of comparison and
decision making. As ‘match’ is the decision coming out of the comparison (3.5.7) process, its use as a verb is
deprecated in favour of compare.
© ISO/IEC 2017 – All rights reserved 7

---------------------- Page: 12 ----------------------
ISO/IEC 2382-37:2017(E)

3.3.32
mated (adjective)
of or having to do with a paired biometric probe (3.3.14) and biometric reference (3.3.16) that are from
the same biometric characteristic (3.1.2) of the same biometric data subject (3.7.5)
Note 1 to entry: While ‘match (3.3.31)’ is the result of a biometric comparison decision (3.3.26), ‘mated’ is a
statement, based on non-biometric information, concerning the origin of the source of the biometric probe
(3.3.14) and the biometric reference (3.3.16).
3.3.33
non-match (noun)
comparison decision (3.3.26) stating that the biometric probe(s) (3.3.14) and the biometric reference
(3.3.16) are not from the same source
3.3.34
non-mated (adjective)
of or having to do with a paired biometric probe (3.3.14) and biometric reference (3.3.16) that are not
from the same biometric characteristic (3.1.2) of the same biometric data subject (3.7.5)
Note 1 to entry: While ‘non-match (3.3.33)’ is the result of a biometric comparison decision (3.3.26), ‘non-mated’
is a statement, based on non-biometric information, concerning the origin of the source of the biometric probe
(3.3.14) and the biometric reference (3.3.16).
3.3.35
similarity score
comparison score (3.3.27) that increases with similarity
3.3.36
threshold (noun)
numerical value (or set of values) at which a decision boundary exists
3.3.37
unidentified biometric data
biometric data (3.3.6) whose biometric data subject (3.7.5) is currently unknown
3.3.38
conformant biometric reference rate
proportion of biometric enrolment data records (3.3.10) containing biometric references (3.3.16)
conformant with system policy
Note 1 to entry: Some biometric systems (3.2.3) require the enrolment of all applicants regardless of the
availability of acquirable biometric characteristics (3.1.2). This ratio, which depends upon system capabilities
and policies regulating acquisition of biometric samples (3.3.21), characterizes the percentage of a given enrolled
population that has conformant biometric references (3.3.16) in the biometric enrolment data records
...