BS ISO/IEC 19795-1:2021
$215.11
Information technology. Biometric performance testing and reporting – Principles and framework
Published By | Publication Date | Number of Pages |
BSI | 2021 | 88 |
This document:
-
establishes general principles for testing the performance of biometrics systems in terms of error rates and throughput rates for purposes including measurement of performance, prediction of performance, comparison of performance, and verifying conformance with specified performance requirements;
-
specifies performance metrics for biometric systems;
-
specifies requirements on the recording of test data and reporting of test results; and
-
specifies requirements on test protocols in order to:
-
reduce bias due to inappropriate data collection or analytic procedures;
-
help achieve the best estimate of field performance for the expended effort;
-
improve understanding of the limits of applicability of the test results.
-
This document is applicable to empirical performance testing of biometric systems and algorithms through analysis of the comparison scores and decisions output by the system, without requiring detailed knowledge of the system’s algorithms or of the underlying distribution of biometric characteristics in the population of interest.
Not within the scope of this document is the measurement of error and throughput rates for people deliberately trying to subvert the intended operation of the biometric system (e.g. by presentation attacks).
PDF Catalog
PDF Pages | PDF Title |
---|---|
2 | National foreword |
8 | Foreword |
9 | Introduction |
11 | 1 Scope 2 Normative references 3 Terms and definitions |
15 | 4 Abbreviated terms |
16 | 5 Conformance 6 General biometric system 6.1 Conceptual representation of general biometric system |
17 | 6.2 Conceptual components of a general biometric system 6.2.1 Data capture subsystem 6.2.2 Transmission subsystem 6.2.3 Signal processing subsystem |
18 | 6.2.4 Data storage subsystem 6.2.5 Comparison subsystem 6.2.6 Decision subsystem |
19 | 6.2.7 Administration subsystem 6.2.8 Interface to external application 6.3 Functions of general biometric system 6.3.1 Enrolment |
20 | 6.3.2 Verification of a positive biometric claim |
21 | 6.3.3 Identification 6.4 Enrolment, verification and identification transactions |
22 | 6.5 Performance measures 6.5.1 Error rates 6.5.2 Throughput rates |
23 | 6.5.3 Types of performance testing 7 Planning the evaluation 7.1 General |
24 | 7.2 Determine information about the system |
25 | 7.3 Controlling factors that influence performance |
26 | 7.4 Test subject selection |
27 | 7.5 Test size 7.5.1 General 7.5.2 Collecting multiple recognition transactions per test subject per system |
28 | 7.5.3 Requirements on test size 7.6 Multiple tests |
29 | 8 Data collection 8.1 Avoidance of data collection errors 8.2 Data and details collected |
30 | 8.3 Enrolments 8.3.1 Enrolment transactions |
31 | 8.3.2 Enrolment conditions 8.3.3 Enrolment failures and presentation errors |
32 | 8.4 One-to-one comparison trials 8.4.1 General 8.4.2 Collection conditions 8.4.3 Frequency of use |
33 | 8.4.4 Systems performing optimization based on enrolled references 8.4.5 Systems performing reference adaptation 8.4.6 Processes for data entry errors and system misuse 8.4.7 Failures to acquire 8.4.8 Adding test data to the corpus 8.4.9 Online comparison trials |
34 | 8.4.10 Offline comparison trials |
35 | 8.4.11 Offline non-mated comparison trials when references are dependent 8.4.12 Offline non-mated comparison trials based on comparison of references 8.4.13 Use of samples from multi-capture comparison transactions |
36 | 8.5 Identification trials 8.5.1 General 8.5.2 Identification testing with non-enrolled test subjects 8.5.3 Use of jack-knife approach for identification testing 9 Analyses 9.1 General |
37 | 9.2 Performance of biometric enrolment 9.2.1 Failure-to-enrol rate 9.2.2 Enrolment transaction duration |
38 | 9.3 Performance of biometric acquisition 9.3.1 Failure-to-acquire rate 9.3.2 Acquisition process duration 9.3.3 Other aspects of acquisition performance |
39 | 9.4 One-to-one comparison performance 9.4.1 False non-match rate 9.4.2 False match rate |
40 | 9.5 Verification system performance metrics 9.5.1 General 9.5.2 False reject rate |
41 | 9.5.3 False accept rate 9.5.4 Verification transaction duration 9.5.5 Generalized false reject rate and generalized false accept rate |
42 | 9.6 Identification system performance metrics 9.6.1 General |
43 | 9.6.2 False-negative identification rate 9.6.3 False-positive identification rate |
44 | 9.6.4 Generalized false-negative identification rate and generalized false-positive identification rate 9.6.5 Selectivity 9.6.6 Closed-set test of identification performance |
45 | 9.6.7 Estimation of identification error rates from one-to-one comparison results 9.6.8 Predicting identification error rates in larger populations |
46 | 9.7 Analysis of performance across controlled experimental factors 9.7.1 Longitudinal analyses 9.7.2 Pairwise analyses 9.8 Detection error trade-off |
47 | 9.9 Transaction durations 9.10 Computational workload |
48 | 9.11 Uncertainty of estimates |
49 | 10 Graphical presentation of results 10.1 Score distributions 10.1.1 General 10.1.2 Boxplots 10.2 Error rate vs threshold plot |
50 | 10.3 DET plot |
52 | 10.4 CMC plot / FNIR over rank plot |
54 | 10.5 FNIR over number of enrolees plot |
55 | 10.6 Heat maps |
56 | 11 Record keeping |
57 | 12 Reporting performance results 12.1 Reporting test details |
58 | 12.2 Summary statistics 12.3 Reporting enrolment performance 12.4 Reporting acquisition performance |
59 | 12.5 Reporting one-to-one comparison performance 12.6 Reporting verification system performance 12.7 Reporting identification system performance |
60 | 12.8 Reporting performance across factors |
62 | Annex A (informative) Differences between evaluation types |
63 | Annex B (Informative) Test size and random uncertainty |
71 | Annex C (informative) Factors influencing performance |
76 | Annex D (Informative) Pre-selection algorithm performance |
78 | Annex E (informative) Identification performance as a function of database size |
79 | Annex F (informative) Algorithms for generating DET and CMC |
82 | Annex G (informative) DET properties and interpretation |
86 | Bibliography |