1、 INCITS/ISO/IEC 29794-1-2010 Information technology Biometric sample quality Part 1: Framework Reaffirmed as INCITS/ISO/IEC 29794-1:2009 R2015INCITS/ISO/IEC 29794-1-2010 PDF disclaimer This PDF file may contain embedded typefaces. In accordance with Adobes licensing policy, this file may be printed
2、or viewed but shall not be edited unless the typefaces which are embedded are licensed to and installed on the computer performing the editing. In downloading this file, parties accept therein the responsibility of not infringing Adobes licensing policy. The ISO Central Secretariat accepts no liabil
3、ity in this area. Adobe is a trademark of Adobe Systems Incorporated. Details of the software products used to create this PDF file can be found in the General Info relative to the file; the PDF-creation parameters were optimized for printing. Every care has been taken to ensure that the file is sui
4、table for use by ISO member bodies. In the unlikely event that a problem relating to it is found, please inform the Central Secretariat at the address given below. Adopted by INCITS (InterNational Committee for Information Technology Standards) as an American National Standard. Date of ANSI Approval
5、: 1/19/2010 Published by American National Standards Institute, 25 West 43rd Street, New York, New York 10036 Copyright 2010 by Information Technology Industry Council (ITI). All rights reserved. These materials are subject to copyright claims of International Standardization Organization (ISO), Int
6、ernational Electrotechnical Commission (IEC), American National Standards Institute (ANSI), and Information Technology Industry Council (ITI). Not for resale. No part of this publication may be reproduced in any form, including an electronic retrieval system, without the prior written permission of
7、ITI. All requests pertaining to this standard should be submitted to ITI, 1250 Eye Street NW, Washington, DC 20005. Printed in the United States of America ii ITIC 2010 All rights reserved INCITS/ISO/IEC 29794-1-2010 ITIC 2010 All rights reserved iiiContents Page Foreword iv Introduction. v 1 Scope
8、1 2 Conformance . 1 3 Normative references 1 4 Terms and definitions . 2 5 Acronyms and abbreviated terms . 5 6 General biometric system 5 7 Biometric sample quality criteria. 5 7.1 Reference model 5 7.2 Quality components: character, fidelity, utility 6 7.3 Usefulness of quality data 7 7.3.1 Real-t
9、ime quality assessment 7 7.3.2 Use in different applications 7 7.3.3 Use as a survey statistic. 7 7.3.4 Accumulation of relevant statistics. 8 7.3.5 Reference dataset improvement 8 7.3.6 Quality-based conditional processing 8 7.3.7 Interchange of quality data by disparate systems. 8 8 Data interchan
10、ge format field definition . 9 8.1 Data fields 9 8.2 Quality score 9 8.2.1 Purpose 9 8.2.2 Data transformation considerations 10 8.2.3 Failure modes 10 8.2.4 Resolution 10 8.2.5 Summarization. 10 8.3 Quality algorithm identification (QAID). 10 8.3.1 Overview. 10 8.3.2 Methodology 10 8.4 Standardized
11、 exchange of quality algorithm results. 11 9 Normalization. 12 Annex A (informative) Procedures to construct a quality score normalization dataset . 13 Annex B (informative) Example - standardized exchange of quality algorithm results 19 Annex C (informative) Procedures for aggregation of utility-ba
12、sed quality scores 21 Bibliography 23 INCITS/ISO/IEC 29794-1-2010 iv ITIC 2010 All rights reservedForeword ISO (the International Organization for Standardization) and IEC (the International Electrotechnical Commission) form the specialized system for worldwide standardization. National bodies that
13、are members of ISO or 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 internati
14、onal 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. International Standards are drafted in accordance with the rules given in t
15、he ISO/IEC Directives, Part 2. The main task of the joint technical committee is to prepare International Standards. Draft International Standards adopted by the joint technical committee are circulated to national bodies for voting. Publication as an International Standard requires approval by at l
16、east 75 % of the national bodies casting a vote. Attention is drawn to the possibility that some of the elements of this document may be the subject of patent rights. ISO and IEC shall not be held responsible for identifying any or all such patent rights. ISO/IEC 29794-1 was prepared by Joint Techni
17、cal Committee ISO/IEC JTC 1, Information technology, Subcommittee SC 37, Biometrics. ISO/IEC 29794 consists of the following parts, under the general title Information technology Biometric sample quality: Part 1: Framework Part 4: Finger image data Technical Report Part 5: Face image data Technical
18、Report Future parts of ISO/IEC 29794 will address other modalities specified by ISO/IEC 19794, with part numbers and titles aligned appropriately. However, as ISO/IEC 29794-1 is intended for use by all modalities, a modality does not necessarily need a modality-specific part in order to make use of
19、quality scores. It is anticipated that a future version of each part of ISO/IEC 19794 will normatively reference ISO/IEC 29794-1, and their respective data fields will be updated as required. INCITS/ISO/IEC 29794-1-2010 ITIC 2010 All rights reserved vIntroduction Quality metrics are useful for sever
20、al applications in the field of biometrics. ISO/IEC 19784-1 specifies a structure and gives guidelines for quality score categorization, and ISO/IEC 29794 defines and specifies methodologies for objective, quantitative quality score expression, interpretation, and interchange. This part of ISO/IEC 2
21、9794 is intended to add value to a broad spectrum of applications in a manner that a) encourages competition, innovation, interoperability and performance improvements; and b) avoids bias towards particular applications, modalities, or techniques. This part of ISO/IEC 29794 presents several biometri
22、c sample quality scoring tools, the use of which is generally optional but can be determined to be mandatory by particular application profiles or specific implementations. A number of applications can benefit from the use of biometric sample quality data; an example is the use of real-time quality
23、feedback upon enrolment to improve the operational efficiency and performance of a biometric system. The association of quality data with biometric samples is an important component of quality metric standardization. Quality fields as specified in 8.1 will be incorporated into data interchange forma
24、ts. If a CBEFF header is present, then CBEFF_BDB_quality can additionally be used to express quality data. Useful analyses can be performed using quality data along with other data in order to improve the performance of a biometric system. For example, correlating quality data to other system metric
25、s can be used to diagnose problems and highlight potential areas of performance improvement. AMERICAN NATIONAL STANDARD INCITS/ISO/IEC 29794-1-2010 ITIC 2010 All rights reserved 1Information technology Biometric sample quality Part 1: Framework 1 Scope For any or all biometric sample types as necess
26、ary, this part of ISO/IEC 29794 1. establishes terms and definitions that are useful in the specification, and use of quality metrics; 2. recommends the purpose and interpretation of biometric quality scores; 3. defines the format and placement of quality data fields in biometric data interchange fo
27、rmats; 4. suggests methods for developing biometric sample datasets for the purpose of quality score normalization; and 5. suggests a format for exchange of quality algorithm results. Outside the scope are the following: 1. the specification of minimum requirements for sample, module, or system qual
28、ity scores; 2. performance assessment of quality algorithms; and 3. standardization of quality algorithms. 2 Conformance A block of quality data is in conformity with this part of ISO/IEC 29794 if it conforms to the normative requirements of Clause 8. 3 Normative references The following referenced
29、documents are indispensable for the application of this document. For dated references, only the edition cited applies. For undated references, the latest edition of the referenced document (including any amendments) applies. 19794-1:2006, Information technology Biometric data interchange formats Pa
30、rt 1: Framework 19785-2:2006, Information technology Common Biometric Exchange Formats Framework Part 2: Procedures for the operation of the Biometric Registration Authority INCITS/ISO/IEC 29794-1-2010 2 ITIC 2010 All rights reserved4 Terms and definitions For the purposes of this document, the foll
31、owing terms and definitions apply. 4.1 acquisition fidelity fidelity of a sample attributed to the acquisition process 4.2 biometric failure to enrol failure of the biometric system to store a usable biometric reference due to deficiencies in the biometric data during an enrolment application NOTE 1
32、 Deficiencies in the biometric data can result from failure to capture an adequate or usable biometric sample, failure to extract adequate or usable biometric features from the sample, or failure to generate an adequate or usable biometric reference from the biometric features. NOTE 2 See SC 37 N SD
33、2 for most recent definition. 4.3 biometric failure to enrol rate proportion of biometric enrolment sessions that resulted in a biometric failure to enrol for other than non-biometric reasons NOTE 1 Basing the denominator on the number of biometric enrolment sessions can result in a higher value tha
34、n basing it on the number of biometric capture subjects. NOTE 2 The proportion denominator is the number of biometric enrolment sessions, excluding those sessions that failed to complete for non-biometric reasons. NOTE 3 See SC 37 N SD2 for most recent definition. 4.4 character contributor to qualit
35、y of a sample attributable to inherent features of the source 4.5 environment physical surroundings and conditions where biometric capture occurs, including operational factors such as operator skill and enrolee cooperation level 4.6 extraction fidelity component of the fidelity of a sample attribut
36、ed to the biometric feature extraction process 4.7 extrinsic quality score requiring reference to an external source, such as a standard, register, or technical specifications, for full interpretation and normalization 4.8 fidelity expression of how accurately a biometric sample represents its sourc
37、e biometric characteristic NOTE The fidelity of a sample comprises components attributable to one or more of the processing steps: acquisition, extraction, signal processing. INCITS/ISO/IEC 29794-1-2010 ITIC 2010 All rights reserved 34.9 intrinsic quality score conveying fully interpreted, normalize
38、d data without the requirement for additional extrinsic information for quality score normalization 4.10 interpretation process of analyzing a quality score along with other data in order to give that score contextual, relative meaning 4.11 failure to acquire rate proportion of the biometric applica
39、tion attempts that resulted in failure to acquire an adequate or usable biometric sample, for other than non-biometric reasons NOTE 1 The proportion denominator is the number of biometric enrolment attempts, excluding those attempts that failed to complete for non-biometric reasons. NOTE 2 See SC 37
40、 N SD2 for most recent definition. 4.12 false match rate FMR proportion of the completed biometric non-match trials that result in a false match NOTE 1 The value computed for the false match rate will depend on thresholds, and other parameters of the comparison process, and the protocol defining the
41、 biometric non-match trials. In particular, treatment of comparisons between identical twins, completely different biometric characteristics of different individuals, such as face topography and Galton ridges, and different but related biometric characteristics from t he same individual, such as lef
42、t and right hand topography, will need proper consideration. See ISO 19795-1. NOTE 2 “Completed” refers to the computational processes required to make a comparison decision, i.e. failures to decide are excluded. NOTE 3 See SC 37 N SD 2 for most recent definition. 4.13 false non-match rate FNMR prop
43、ortion of the completed biometric match trials that result in a false non-match NOTE 1 The value computed for the false non-match rate will depend on thresholds and other parameters of the comparison process, and the protocol defining the biometric match trials. NOTE 2 “Completed” refers to the comp
44、utational processes required to make a comparison decision, i.e. failures to decide are excluded. NOTE 3 See SC 37 N SD2 for most recent definition. 4.14 operator individual who processes a user in a biometric system, performing or supervising capture and recapture 4.15 performance assessment of the
45、 FMR, FNMR, failure to enrol rate and failure to acquire rate of a biometric system INCITS/ISO/IEC 29794-1-2010 4 ITIC 2010 All rights reserved4.16 quality degree to which a biometric sample fulfils specified requirements for a targeted application NOTE Specified quality requirements can address asp
46、ects of quality such as focus, resolution, etc. Implicit quality requirements address the likelihood of achieving a correct matching result. 4.17 quality score quantitative expression of quality 4.18 quality score normalization rescaling of quality scores to improve consistency in scale and interpre
47、tation 4.19 quality score normalization dataset QSND dataset of biometric samples annotated with quality scores for use in quality score normalization NOTE Target quality scores can be assigned on the basis of performance outcomes using the sample in question, or can be based on quality factors reco
48、rded in acquisition of the dataset. 4.20 quality score percentile rank QSPR percentile rank of the quality score of a biometric sample, derived from its own utility score and those of other samples in an identified control dataset cf. quality score normalization dataset 4.21 raw quality score qualit
49、y score that has not been interpreted, either by the creator or recipient of the score, and alone can not intrinsically provide contextual information 4.22 sample image, signal, or pattern based interpretation of a physical human feature used for identification or verification using biometric techniques 4.23 source physical body part or function represented by a biometric sample 4.24 utility observed performance of
