Upload
osborn-hoover
View
241
Download
1
Tags:
Embed Size (px)
Citation preview
WG3 report on Biometric Data Format and Related Standards
WG3 report on Biometric Data Format and Related Standards
Christoph Busch
- ISO/IEC JTC1/SC37 WG3 Convenor -
Darmstadt 2014-01-20
2Christoph Busch
Meetings
Winchester
• 2013-04-22 to 2013-04-26
• THANKS to the UK for hosting us
Darmstadt
• 2014-01-13 to 2014-01-172
19Christoph Busch
Biometric Data Interchange Formats
19
21Christoph Busch
Generation 2 of ISO/IEC 19794
21
G1
19794-1:2006
-2:2005
-3:2006
-4:2005
-5:2005
-6:2005
-7:2007
-8:2006
-9:2007
-10:2007
-2:2011
-4:2011
-5:2011
-6:2011
-7:201x
-8:2011
-9:2011
-11:2013
-13:201x
-14:2013
19794-1:2011
G2
All partsbinary encoding
the semantic (i.e. general header / structure of representation header)equivalent for binary encoded and XML encoded parts in G2
19794-1 AMD2 XML Framework
19794-1 AMD1 Conformance testing methodology
-2:201x
-4:201x
-5:201x
-6:201x
-7:201x
-9:201x
34Christoph Busch
Part 15: Palm crease image data
34
ISO/IEC 19794-15
• A standard image interchange format for biometric systems that utilize human palm crease pattern images (alias palm lines)
• The format will contain detailed pixel information, units of measurement, description of imaging area of body, and imaging methods such as transparency or reflectance image
35Christoph Busch
Part 15: Palm crease image data
Darmstadt Decisions
• The title will be aligned with ANSI/NIST term„palm crease“
• Draft must be aligned with 19794-4
• Seeking for revised draft
35
36Christoph Busch
Framework for XML Encoding
FDAM ISO/IEC 19794-1:2011 AMD2 XML encoding
• Binary and XML encoding schemes in parallel
• Clause 12 coding schemes for binary format txpes
• Clause 13 coding schemes for xml format type
• Will define common data types (accross several parts) and element names and refer to elements that apply to other SC37 project, which may be promoted to SD16
• Mapping between 19794 data elements and those of ANSI/NIST ITL standard may be included as informative annex as an aid for translation
• Conventions on harmonization of ElementTypes
• Conformance testing of XML-records with schema validation
36
38Christoph Busch
Framework for XML Encoding
ISO/IEC 19794-1:2011 AMD2 XML encoding
• Mapping from common XML elements to binary elements
38
Source: ISO/IEC 19794-1 AMD2: Framework XML Encoding
39Christoph Busch
XML Encoding
Darmstadt Decisions
• ISO/IEC 19794-1:2011 AMD2 - progress: FDAM
• ISO/IEC 19794-2:2011 AMD2 - progress: DAM
• ISO/IEC 19794-4:2011 AMD2 - progress: DAM
• ISO/IEC 19794-5:2011 AMD2 - progress: PDAM
• ISO/IEC 19794-6:2011 AMD2 - progress: 2nd PDAM
• ISO/IEC 19794-7:2011 AMD2 - progress: DAM
• ISO/IEC 19794-9:2011 AMD2 - progress: DAM
39
40Christoph Busch
Conformance Testing Methodology
G1 - 29109-x
• Part 1, 2, 4, 5, 6, 7, 8. 9 and 10 published
• 5th WD 29109-2 AMD1 Level 3 Conformance Testing‣ seeking for empirical studiess
• 2nd rev29109-5 to cover defect reports ‣ this revision will NOT cover the 3D-Face amendment
G2 - 19794-x:2011 AMD1
• Part 1, 2 4 and 9 are published
• Part 5 and 11 are FDAM
• Part 6 is DAM
• Part 14 is PDAM
• tables addressed testing of Binary Encoded Records only
• adaptation for XML- will be done in AMD240
41Christoph Busch
Conformance Testing
41
Minutiae Detection Deficiency
Vendor AVendor BVendor C
42Christoph Busch
Conformance Testing
42
• ISO/IEC 29109 - Part2: Finger minutiae data
• ISO/IEC 29109-2 AMD1: Semantic conformance testing - Part2: Finger minutiae data‣ Scope: tests of semantic assertions
‣ Type A Level 3 as defined in ISO/IEC 29109-1:2009
43Christoph Busch
Related Standards and Trends
43
44Christoph Busch
Biometric Sample Quality
Revision running for
• ISO/IEC 29794 Part 1: framework
• ISO/IEC 29794 Part 4: finger image data‣ upgrade from TR to IS to incorporate NFIQ2.0 findings
see: http://www.nist.gov/itl/iad/ig/development_nfiq_2.cfm
• 2nd DIS ISO/IEC 29794 Part 6: iris image data
44
46Christoph Busch
Biometric Sample Quality
Revision ISO/IEC 29794-1:201x
Definitions
• Same as before, but allow for a vector of quality components
Goal:
• Actionable quality
• Each element of quality vector has a score from 0 to 100.
46
Source: ISO/IEC 29794-1
47Christoph Busch
Biometric Sample Quality
Revision ISO/IEC 29794-1:201x
Darmstadt Decisions
• 29794-1 shall support both BIN and XML
• No 250 multi-QualityBlock encoding
• A QualityVector must be transcoded to n-quality blocks, in order to maintain compatibility with 19794-1:2011
• QualityVector in a container structure should be supported
• do not progress: 2nd CD
47
48Christoph Busch
Biometric Sample Quality - Iris
DIS ISO/IEC 29794-6 iris image data
• Scope: ‣ methods used to quantify the quality of iris images,
‣ normative requirements on software and hardware producing iris images,
‣ normative requirements on software and hardware measuring the utility of iris images,
‣ terms and definitions for quantifying iris image quality, and
‣ a standardized encoded iris image quality data record.
48
50Christoph Busch
Biometric Sample Quality - Iris
Revision ISO/IEC 29794-6:201x
Darmstadt Decisions
• Computational method for PUPIL_BOUNDARY_CIRCULARITYis fixed
• clarification on human iris sizes
• introduce measures from PL to calcurlate sharpness
• do not progress: 2nd DIS
50
51Christoph Busch
Biometric Sample Quality - Finger
Revision ISO/IEC 29794-4:201x
Darmstadt Decisions
• Limit to one single Gabor method
• More examples will be included
• Not compute area of overlap for image-pairs due to lack of quantative measure
• do not progress: 3rd WD
51
53Christoph Busch
Presentation Attack Detection
53
ISO/IEC 30107 - Scope
• terms and definitions that are useful in the specification, characterization and evaluation of presentation attack detection methods;
• a common data format for conveying the type of approach used and the assessment of presentation attack in data formats;
• principles and methods for performance assessment of presentation attack detection algorithms or mechanisms; and
• a classification of known attacks types (in an informative annex).
Outside the scope are
• standardization of specific PAD detection methods;
• detailed information about countermeasures (i.e. anti-spoofing techniques), algorithms, or sensors;
• overall system-level security or vulnerability assessment.
57Christoph Busch 57
Presentation Attack Detection
Error Rates in ISO/IEC 30107
• Detection might result in errors
‣presentation attack detection rate (PADR)„proportion of presentation attacks with a defined level of difficulty detected by a system.“
‣presentation attack non-detection rate (PA-NDR)„proportion of presentation attacks with a defined level of difficulty not detected by a system.“
• Note of caution: For security assessment rates are irrelevant, if there exists a single artefact that can break the system
‣presentation attack detection-power level:„level of difficulty of biometric presentation attacks above which the biometric system is not able to detect them.“
58Christoph Busch
Presentation Attack Detection
Darmstadt Decisions
• Encoding of PAD data is not depended on 19794 G2-G3 discussion. A PAD data record will be agnostic about in which structure it is incorporated
• PAD sub-results should be collected in a vector -thus extended data will be included in a PAD record‣ extended data can be either proprietary or standardized
(i.e. vendor-ID = 0101, which is „ISO/IEC JTC 1 SC 37-Biometrics“)
• PAD data record definition‣ Tags are defined starting with 8 indicating a compund data
• New PAD metrics
• 3-part split as some parts are ready to move to CD
58
59Christoph Busch
Presentation Attack Detection
Darmstadt Decisions on New 30107 parts
• Part 1 (IS) - Framework ‣ Elaine Newton
‣ Cl. 1 -6
‣ progress: CD
• Part 2 (IS) - Data formats ‣ Olaf Henniger
‣ Cl. 7
‣ do not progress: WD
• Part 3 (IS) Testing, Reporting and Classification of Attacks ‣ (Michael Thieme)
‣ Annex A+C
‣ Annex C will be promoted to a Clause
‣ do not progress: WD59
61Christoph Busch
New project
CCTV
• DRAFT RESOLUTION G.6 – Work on CCTVAs Australia has changed its vote on SC 37 N5630, the Proposal for a New Work Item on Use of operator-assisted automated face recognition in CCTV systems – Part 1: Recommendations on design and specification and Part 2: Recommendations on testing and reporting practice has now passed and will be added to the SC 37 program of work.
• SC 37 reviewed ...• As a result of this review, SC 37 resolves that SC 37 N5629 and
N5630 be merged into one multipart project (30137) with the following structure and placement:
• Part 1, Design and specification (WG 4)• Part 2, Performance testing and reporting (WG 5)• Part 3, Data formats (WG 3)
61
62Christoph Busch
G3 road
Data Interchange Format
• Widely adopted and deployed in large number• Reflecting need for distributed systems with XML encoding• Reflecting need for actionalbe feedback wtih quality vectors• Reflecting need for secure system with PAD encoding
Preliminary Discussion with SC17 WG3• Definition on transition period from G1 to G2 in ICAO 9393• Suitable revision cycles for definition in ICAO 9303• Forward and backwards compatibility• Transcodability from XML to BIN and vice versa
Working on concepts in a Special group
62
63Christoph Busch
Conclusion
Thank you for your support
63
64Christoph Busch
Conclusion
Thank you for your support
64
66Christoph Busch
References
Information on WG3 status
• and a ppt-copy of theses slides
• are available at:
http://www.christoph-busch.de/standards-sc37wg3.html
66
67Christoph Busch
References
List of projects
• and a ppt-copy of theses slides
• are available at:
http://www.christoph-busch.de/standards-sc37wg3.html
67