1、BRITISH STANDARD BS ISO/IEC 19795-1:2006 Information technology Biometric performance testing and reporting Part 1: Principles and framework ICS 35.040 BS ISO/IEC 19795-1:2006 This British Standard was published under the authority of the Standards Policy and Strategy Committee on 28 April 2006 BSI
2、2006 ISBN 0 580 48182 4 National foreword This British Standard reproduces verbatim ISO/IEC 19795-1:2006 and implements it as the UK national standard. The UK participation in its preparation was entrusted to Technical Committee IST/44, Biometrics, which has the responsibility to: A list of organiza
3、tions represented on this committee can be obtained on request to its secretary. Cross-references The British Standards which implement international publications referred to in this document may be found in the BSI Catalogue under the section entitled “International Standards Correspondence Index”,
4、 or by using the “Search” facility of the BSI Electronic Catalogue or of British Standards Online. This publication does not purport to include all the necessary provisions of a contract. Users are responsible for its correct application. Compliance with a British Standard does not of itself confer
5、immunity from legal obligations. aid enquirers to understand the text; present to the responsible international/European committee any enquiries on the interpretation, or proposals for change, and keep UK interests informed; monitor related international and European developments and promulgate them
6、 in the UK. Summary of pages This document comprises a front cover, an inside front cover, the ISO/IEC title page, pages ii to vi, pages 1 to 56, an inside back cover and a back cover. The BSI copyright notice displayed in this document indicates when the document was last issued. Amendments issued
7、since publication Amd. No. Date Comments Reference number ISO/IEC 19795-1:2006(E)INTERNATIONAL STANDARD ISO/IEC 19795-1 First edition 2006-04-01 Information technology Biometric performance testing and reporting Part 1: Principles and framework Technologies de linformation Essais et rapports de perf
8、ormance biomtriques Partie 1: Principes et canevas BS ISO/IEC 19795-1:2006ii iii Contents Page Foreword. v Introduction v 1 Scope. 1 2 Conformance. 1 3 Normative references. 1 4 Terms and definitions. 2 4.1 Biometric data . 2 4.2 User interaction with a biometric system. 3 4.3 Personnel involved in
9、the evaluation . 3 4.4 Types of evaluation 4 4.5 Biometric applications . 5 4.6 Performance measures 5 4.7 Data presentation curves. 7 4.8 Statistical terms 7 5 General biometric system 8 5.1 Conceptual diagram of general biometric system 8 5.2 Conceptual components of a general biometric system 8 5
10、.3 Functions of general biometric system 10 5.4 Enrolment, verification security, including vulnerability; conformance; safety; human factors, including user acceptance; cost/benefit; privacy regulation compliance. Methods and philosophies for these other types of test are currently being considered
11、 internationally by a broad range of groups. The purpose of this part of ISO/IEC 19795 is to present the requirements and best scientific practices for conducting technical performance testing. This is necessary because even a short review of the technical literature on biometric device testing over
12、 the last two decades or more reveals a wide variety of conflicting and contradictory testing protocols 1-11. Even single organizations have produced multiple tests, each using a different test method. Test protocols have varied not only because test goals and available data are different from one t
13、est to the next, but also because no standard has existed for protocol creation. Biometric technical performance testing can be of three types: technology, scenario or operational evaluation. Each type of test requires a different protocol and produces different types of results. Even for tests of a
14、 single type, the wide variety of biometric devices, sensors, vendor instructions, data acquisition methods, target applications and populations makes it impossible to present precise uniform testing protocols. Other parts of ISO/IEC 19795 will provide specific advice and requirements for the develo
15、pment and use of such different test protocols. This part of ISO/IEC 19795 addresses specific philosophies and principles that can be applied over a broad range of test conditions. This part of ISO/IEC 19795 has been developed from the UK Biometrics Working Groups Best Practices in Testing and Repor
16、ting Performance of Biometric Devices 12 which itself drew from two primary source documents developed by the US National Institute of Standards and Technology (NIST) 13, 14, a variety of evaluation reports 7-10, and comments from the Biometrics Consortium Working Group on Interoperability, Performa
17、nce and Assurance. BS ISO/IEC 19795-1:20061 Information technology Biometric performance testing and reporting Part 1: Principles and framework 1 Scope This part of ISO/IEC 19795 establishes general principles for testing the performance of biometric systems in terms of error rates and throughput ra
18、tes for purposes including prediction of performance, comparison of performance, and verifying compliance with specified performance requirements; specifies performance metrics for biometric systems; specifies requirements on test methods, recording of data and reporting of results; and provides a f
19、ramework for developing and describing test protocols, to help avoid bias due to inappropriate data collection or analytic procedures, to help achieve the best estimate of field performance for the expended effort, and to improve understanding of the limits of applicability of the test results. This
20、 part of ISO/IEC 19795 is applicable to empirical performance testing of biometric systems and algorithms through analysis of the matching scores and decisions output by the system, without detailed knowledge of the systems algorithms or of the underlying distribution of biometric characteristics in
21、 the population of interest. Not within the scope of this part of ISO/IEC 19795 is the measurement of error and throughput rates for people deliberately trying to circumvent correct recognition by the biometric system (i.e. active impostors). 2 Conformance To conform to this part of ISO/IEC 19795, a
22、 biometric performance test shall be planned, executed and reported in accordance with the mandatory requirements contained herein. 3 Normative references The following referenced documents are indispensable for the application of this document. For dated references, only the edition cited applies.
23、For undated references, the latest edition of the referenced document (including any amendments) applies. ISO/IEC 17025, General requirements for the competence of testing and calibration laboratories BS ISO/IEC 19795-1:20062 4 Terms and definitions For the purposes of this document, the following t
24、erms and definitions apply. 4.1 Biometric data 4.1.1 sample users biometric measures as output by the data capture subsystem EXAMPLE Fingerprint image, face image and iris image are samples. NOTE In more complex systems, the sample may consist of multiple presented characteristics (e.g., 10-print fi
25、ngerprint record, face image captured from different angles, left and right iris image pair). 4.1.2 features digital representation of the information extracted from a sample (by the signal processing subsystem) that will be used to construct or compare against enrolment templates EXAMPLE Minutiae c
26、oordinates and principal component coefficients are features. 4.1.3 template model users stored reference measure based on features extracted from enrolment samples NOTE The reference measure is often a template comprising the biometric features for an ideal sample presented by the user. More genera
27、lly, the stored reference will be a model representing the potential range of biometric features for that user. In this part of ISO/IEC 19795, we normally use “template” to include “model”. 4.1.4 matching score similarity score measure of the similarity between features derived from a sample and a s
28、tored template, or a measure of how well these features fit a users reference model NOTE 1 A match or non-match decision may be made according to whether this score exceeds a decision threshold. NOTE 2 As features derived from a presented sample become closer to the stored template, similarity score
29、s will increase. 4.1.5 verification decision determination of the probable validity of a users claim to identity in the system 4.1.6 candidate list set of potential enrolled identifiers for a subject produced by an identification attempt (or by a pre-selection algorithm) 4.1.7 identification decisio
30、n determination of a candidate list for the users probable identity in the system BS ISO/IEC 19795-1:20063 4.2 User interaction with a biometric system 4.2.1 presentation submission of a single biometric sample on the part of a user 4.2.2 attempt submission of one (or a sequence of) biometric sample
31、s to the system NOTE An attempt results in an enrolment template, a matching score (or scores), or possibly a failureto-acquire. 4.2.3 transaction sequence of attempts on the part of a user for the purposes of an enrolment, verification or identification NOTE There are three types of transaction: en
32、rolment sequence, resulting in an enrolment or a failure-to-enrol; a verification sequence resulting in a verification decision; or identification sequence, resulting in an identification decision. 4.2.4 genuine attempt single good-faith attempt by a user to match their own stored template 4.2.5 zer
33、o-effort impostor attempt attempt in which an individual submits his/her own biometric characteristics as if he/she were attempting successful verification against his/her own template, but the comparison is made against the template of another user 4.2.6 active impostor attempt attempt in which an
34、individual tries to match the stored template of a different individual by presenting a simulated or reproduced biometric sample, or by intentionally modifying his/her own biometric characteristics NOTE Error rates for active impostor attempts will vary from those for zero-effort impostor attempts.
35、Defining the methods and skill used in active impostor attempts is outside the scope of this part of ISO/IEC 19795. 4.2.7 presentation effects broad category of variables affecting the way in which the users inherent biometric characteristics are displayed to the sensor EXAMPLE In facial recognition
36、, this could include pose angle and illumination; in fingerprinting, finger rotation and skin moisture. In many cases, the distinction between changes in the fundamental biometric characteristic and the presentation effects may not be clear (e.g. facial expression in facial recognition or pitch chan
37、ge in speaker verification systems). 4.2.8 channel effects changes imposed on the presented signal in the transduction and transmission process due to the sampling, noise and frequency response characteristics of the sensor and transmission channel 4.3 Personnel involved in the evaluation 4.3.1 user person presenting a biometric sample to the system BS ISO/IEC 19795-1:2006
