BS ISO/IEC 19795-1:2006
Superseded
A superseded Standard is one, which is fully replaced by another Standard, which is a new edition of the same Standard.
A superseded Standard is one, which is fully replaced by another Standard, which is a new edition of the same Standard.
Hardcopy , PDF
06-01-2021
English
04-18-2006
Foreword
Introduction
1 Scope
2 Conformance
3 Normative references
4 Terms and definitions
4.1 Biometric data
4.2 User interaction with a biometric system
4.3 Personnel involved in the evaluation
4.4 Types of evaluation
4.5 Biometric applications
4.6 Performance measures
4.7 Data presentation curves
4.8 Statistical terms
5 General biometric system
5.1 Conceptual diagram of general biometric system
5.2 Conceptual components of a general biometric system
5.3 Functions of general biometric system
5.4 Enrolment, verification & identification transactions
5.5 Performance measure
6 Planning the evaluation
6.1 General
6.2 Use of other parts of ISO/IEC 19795
6.3 Determine information about the system
6.4 Controlling factors that influence performance
6.5 Test subject selection
6.6 Test size
6.7 Multiple tests
7 Data collection
7.1 Avoidance of data collection errors
7.2 Data and details collected
7.3 Enrolments
7.4 Genuine transactions
7.5 Identification transactions of users enrolled in
the system
7.6 Impostor transactions
7.7 Identification transactions of users not enrolled
in the system
8 Analyses
8.1 General
8.2 Fundamental performance metrics
8.3 Verification system performance metrics
8.4 (Open-set) Identification system performance metrics
8.5 Closed-set identification
8.6 Detection error trade-off/Receiver operating
characteristic curves
8.7 Uncertainty of estimates
9 Record keeping
10 Reporting performance results
10.1 Fundamental metrics
10.2 Verification system metrics
10.3 Identification system metrics
10.4 Closed-set identification system metrics
10.5 Reporting test details
10.6 Graphical presentation of results
Annex A (informative) Differences between evaluation types
Annex B (informative) Test size and uncertainty
B.1 Confidence intervals and test size assuming independent
identically distributed comparisons
B.1.1 Rule of 3
B.1.2 Rule of 30
B.1.3 Number of comparisons to support a claimed
error rate
B.2 Variance of performance measures as a function of
test size
B.3 Estimates for variance of performance measures
B.3.1 General
B.3.2 Variance of observed false non-match rate
B.3.3 Variance of observed false match rate
B.4 Estimating confidence intervals
B.4.1 General
B.4.2 Bootstrap estimates of the variance and
confidence intervals
B.4.3 Subset sampling
Annex C (informative) Factors influencing performance
C.1 General
C.2 List of factors
C.2.1 Population demographics
C.2.2 Application
C.2.3 User physiology
C.2.4 User behaviour
C.2.5 User appearance
C.2.6 Environmental influences
C.2.7 Sensor and hardware
C.2.8 User interface
C.3 Examples for reporting
C.3.1 Finger position
C.3.2 Illumination
C.3.3 Glasses
C.3.4 Dirt on platen
C.3.5 Weather
Annex D (informative) Pre-selection
D.1 Pre-selection algorithm performance
Annex E (informative) Identification performance as a
function of database size
Annex F (informative) Algorithms for generating ROC,
DET and CMC curves
F.1 Algorithm for ROC and DET
F.2 Algorithm for generating CMC
Bibliography
Access your standards online with a subscription
Features
-
Simple online access to standards, technical information and regulations.
-
Critical updates of standards and customisable alerts and notifications.
-
Multi-user online standards collection: secure, flexible and cost effective.