ISO/IEC 19794-5:2011/Amd 1:2014
(Amendment)Information technology — Biometric data interchange formats — Part 5: Face image data — Amendment 1: Conformance testing methodology and clarification of defects
Information technology — Biometric data interchange formats — Part 5: Face image data — Amendment 1: Conformance testing methodology and clarification of defects
Technologies de l'information — Formats d'échange de données biométriques — Partie 5: Données d'image de la face — Amendement 1: Méthodologie d'essai de conformité et précisions concernant les défauts
General Information
Relations
Standards Content (Sample)
INTERNATIONAL ISO/IEC
STANDARD 19794-5
Second edition
2011-11-01
AMENDMENT 1
2014-02-15
Information technology — Biometric data
interchange formats —
Part 5:
Face image data
AMENDMENT 1: Conformance testing
methodology and clarification of defects
Technologies de l'information — Formats d'échange de données
biométrique —
Partie 5: Données d'image de la face
AMENDEMENT 1: Méthodologie d'essai de conformité et précisions
concernant les défauts
Reference number
ISO/IEC 19794-5:2011/Amd.1:2014(E)
©
ISO/IEC 2014
---------------------- Page: 1 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014(E)
COPYRIGHT PROTECTED DOCUMENT
© ISO/IEC 2014
All rights reserved. Unless otherwise specified, no part of this publication may be reproduced or utilized otherwise in any form or by any
means, electronic or mechanical, including photocopying, or posting on the internet or an intranet, without prior written permission.
Permission can be requested from either ISO at the address below or ISO’s member body in the country of the requester.
ISO copyright office
Case postale 56 CH-1211 Geneva 20
Tel. + 41 22 749 01 11
Fax + 41 22 749 09 47
E-mail copyright@iso.org
Web www.iso.org
Published in Switzerland
ii © ISO/IEC 2014 – All rights reserved
---------------------- Page: 2 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Foreword
ISO (the International Organization for Standardization) and IEC (the International Electrotechnical
Commission) form the specialized system for worldwide standardization. National bodies that 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 international 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 the 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 least 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 shall not be held responsible for identifying any or all such patent rights.
Amendment 1 to ISO/IEC 19794-5:2011 was prepared by Joint Technical Committee ISO/IEC JTC 1,
Information technology, Subcommittee SC 37, Biometrics.
©ISO/IEC 2014 – All rights reserved iii
---------------------- Page: 3 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Information technology — Biometric data interchange
formats —
Part 5:
Face image data
AMENDMENT 1: Conformance testing methodology and
clarification of defects
Add to the "Introduction" clause of ISO/IEC 19794-5:2011
The definition of conformance testing (Annex A) is distinct from the ISO/IEC 29109-5, which addressed
conformance testing only of the first, 2005, edition of this part of the ISO/IEC 19794 standard.
Add to the "Scope" clause of ISO/IEC 19794-5:2011
This part of ISO/IEC 19794 also specifies elements of conformance testing methodology, test assertions,
and test procedures as applicable to this part of ISO/IEC 19794. It establishes test assertions pertaining to
the structure of the face image data format (Type A Level 1 as defined in ISO/IEC 19794-1:2011/Amd.1),
test assertions pertaining to internal consistency of the types of values that may be contained within each
field (Type A Level 2 as defined in ISO/IEC 19794-1:2011/Amd.1), and semantic test assertions (Type A
Level 3 as defined in ISO/IEC 19794-1:2011/Amd.1).
The conformance testing methodology specified in this part of ISO/IEC 19794 does not establish:
— tests of other characteristics of biometric products or other types of testing of biometric products (e.g.
acceptance, performance, robustness, security),
— tests of conformance of systems that do not produce data records conforming to the requirements of this
part of ISO/IEC 19794.
Add at the end of clause 3:
“ISO/IEC/IEEE 60559, Information technology — Microprocessor Systems — Floating-Point arithmetic”
Replace in 2nd paragraph of clause 5.5.9.1
“The encoding B of the yaw angle Y shall be in degrees as a byte (1 byte) with values from –180 to 180
Y
modulo 2”
With
“The encoded value, B , shall be stored in 1 byte with values 0 to 180 computed from a real-valued yaw
Y
angle estimate, -180 ≤ Y < 180, as follows”
©ISO/IEC 2014 – All rights reserved 1
---------------------- Page: 4 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Replace in 2nd paragraph of clause 5.5.9.2
“The encoding B of the pitch angle P shall be in degrees as a byte (1 byte) with values from –180 to 180
P
modulo 2”
With
“The encoded value, B , shall be stored in 1 byte with values 0 to 180 computed from a real-valued pitch
P
angle estimate, -180 ≤ P < 180, as follows:"
Replace in 2nd paragraph of clause 5.5.9.3
“The encoding B of the roll angle R shall be in degrees as a byte (1 byte) with values from –180 to 180
R
modulo 2”
With
“The encoded value, B , shall be stored in 1 byte with values 0 to 180 computed from a real-valued roll
R
angle estimate, -180 ≤ R < 180, as follows:”
Replace Figure 9 with
2 ©ISO/IEC 2014 – All rights reserved
---------------------- Page: 5 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Replace Table 15 with
Table 15 — Definitions of the anthropometric landmarks
Point Point Anthropometric
MPEG4 How to point
Identifier Code point name
The highest point of head when the head is
v oriented in Frankfurt Horizon.
1.1 11.4 vertex
Refer to Annex E for the definition of the
Frankfurt Horizon.
g The most prominent middle point between the
1.2 glabella
eyebrows
Situated in the occipital region of the head is
op 1.3 opisthocranion
most distant from the glabella
The most prominent lateral point on each side
eu 1.5, 1.6 eurion of the skull in the area of the parietal and
temporal bones
The point on each side of the forehead, laterally
ft 1.7, 1.8 frontotemporale
from the elevation of the linea temporalis
The point on the hairline in the midline of the
tr 1.9 11.1 trichion
forehead
The most lateral point of each of the zygomatic
zy 2.1, 2.2 zygion
The most lateral point on the mandibural angle
go 2.3,2.4 2.13, 2.14 gonion
close to the bony gonion
Determines the lower border of the lower lip or
sl 2.5 sublabiale
the upper border of the chin
The most anterior midpoint of the chin, located
pg 2.6 2.10 pogonion on the skin surface in the front of the identical
bony landmark of the mandible
menton (or The lowest median landmark on the lower
gn 2.7 2.1
gnathion) border of the mandible
The most lateral point on the surface of the
cdl 2.9, 2.10 condylion laterale
condyle of the mandible
The point at the inner commissure of the eye
en 3.1, 3.2 3.11, 3.8 endocanthion
fissure
exocanthion (or The point at the outer commissure of the eye
ex 3.3, 3.4 3.7, 3.12
ectocanthion) fissure
center point of Is determined when the head is in the rest
p 3.5, 3.6 3.5, 3.6
pupil position and the eye is looking straight forward
The lowest point on the lower margin of each
or 3.7, 3.8 3.9, 3.10 orbitale
orbit
palpebrale The highest point in the midportion of the free
ps 3.9, 3.10 3.1, 3.2
superius margin of each upper eyelid
palpebrale The lowest point in the midportion of the free
pi 3.11, 3.12 3.3, 3.4
inferius margin of each lower eyelid
The highest point on the lower border of the
os 4.1, 4.2 orbitale superius
eyebrow
The highest point on the upper border in the
sci 4.3, 4.4 4.3, 4.4 superciliare
midportion of each eyebrow
The point in the middle of both the nasal root
n 5.1 nasion
and nasofrontal suture
sellion (or Is the deepest landmark located on the bottom
se 5.2
subnasion) of the nasofrontal angle
al 5.3, 5.4 9.1, 9.2 alare The most lateral point on each alar contour
prn 5.6 9.3 pronasale The most protruded point of the apex nasi
©ISO/IEC 2014 – All rights reserved 3
---------------------- Page: 6 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Point Point Anthropometric
MPEG4 How to point
Identifier Code point name
The midpoint of the angle at the columella base
sn 5.7 9.15 subnasale where the lower border of the nasal septum and
the surface of the upper lip meet
The point at the lower limit of each alar base,
sbal 5.9, 5.10 subalare where the alar base disappears into the skin of
the upper lip
alar curvature (or The most lateral point in the curved base line of
ac 5.11, 5.12
alar crest) point each ala
The base of the nasal root medially from each
mf 5.13, 5.14 9.6, 9.7 maxillofrontale
endocanthion
christa philtri The point on each elevated margin of the
cph 6.1, 6.2 8.9, 8.10
landmark philtrum just above the vermilion line
labiale (or labrale) The midpoint of the upper vermillion line
ls 6.3 8.1
superius
labiale (or labrale) The midpoint of the lower vermillion line
li 6.4 8.2
inferius
ch 6.5, 6.6 8.3, 8.4 cheilion The point located at each labial commissure
The imaginary point at the crossing of the
vertical facial midline and the horizontal labial
sto 6.7 stomion
fissure between gently closed lips, with teeth
shut in the natural position
The highest point of the free margin of the
sa 7.1, 7.2 10.1, 10.2 superaurale
auricle
The lowest point of the free margin of the ear
sba 7.3, 7.4 10.5, 10.6 subaurale
lobe
The most anterior point on the ear, located just
pra 7.5, 7.6 10.9, 10.10 preaurale
in front of the helix attachment to the head
The most posterior point on the free margin of
pa 7.7, 7.8 10.3, 10.4 postaurale
the ear
otobasion The point of attachment of the helix in the
obs 7.9, 7.10
superious temporal region
The point of attachment of the ear lobe to the
obi 7.11, 7.12 otobasion infrious
cheek
The highest point of the upper margin of the
po 7.13, 7.14 porion (soft)
cutaneous auditory meatus
t 8.1, 8.2 tragion The notch on the upper margin of the tragus
Replace in clause 5.10.4
“Each factor is represented by a mandatory four byte float value”
With
“Each factor is represented by a mandatory four byte float value and be coded as defined in the
ISO/IEC/IEEE 60559 single precision binary floating-point format, i.e. the ‘binary32’ format. The values NaN
(Not a Number), positive inf (infinity) and negative inf shall not be encoded”
Replace in Clause 14, Table 38, Column 3, Row 2
{iso registration-authority cbeff(19785)organization(0) 257bdbs(0) face-image (8)}
with
{iso(1) registration-authority(1) cbeff(19785) biometric-organization(0) jtc1-sc37(257) bdbs(0) face-image(8)}
4 ©ISO/IEC 2014 – All rights reserved
---------------------- Page: 7 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Replace Annex A with the following one.
Annex A
(normative)
Conformance testing methodology
A.1 Introduction
This normative annex specifies elements of conformance testing methodology, test assertions, and test
procedures as applicable to this part of biometric data interchange format standard. Specifically it
establishes
— test assertions of the structure of the face image data format as specified in this part of ISO/IEC 19794
(Type A Level 1 as defined in ISO/IEC 19794-1:2011/Amd.1),
— test assertions of internal consistency by checking the types of values that may be contained within each
field (Type A Level 2 as defined in ISO/IEC 19794-1:2011/Amd.1),
— tests of semantic assertions (Type A Level 3 as defined in ISO/IEC 19794-1:2011/Amd.1).
This conformance testing metodology does not establish
— tests of conformance of CBEFF structures required by ISO/IEC 19794-1:2011,
— tests of conformance of the image data to the quality-related specifications of ISO/IEC 19794-1:2011,
— tests of conformance of the image data blocks to the respective JPEG or JPEG 2000 standards,
— tests of other characteristics of biometric products or other types of testing of biometric products (e.g.,
acceptance, performance, robustness, security).
The conformance testing methodology specified in ISO/IEC 19794-1:2011/Amd.1 shall apply. The content of
the tables below is based on ISO/IEC 19794-1:2011/Amd.1 and shall only be used in the context of that
conformance testing methodology.
A.2 Table of requirements
The normative requirements are listed in Table 1. The supplier of the IUT can explain which optional
components of the standard are supported and the testing laboratory can note the results of the test.
Under subformat applicability the columns labelled B, F, T, P indicate the Basic, Full Frontal, Token Frontal
and Post-Processed image types.
©ISO/IEC 2014 – All rights reserved 5
---------------------- Page: 8 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Table A.1 — Normative requirements
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body
B F T P
5.1 The ISO/IEC 19794-5 BDIR format specified in this part of ISO/IEC 19794 is a format to store 3C O-1 Y Y Y
R-1 Y
face representations within a biometric data record.
5.1 Each BDIR shall pertain to a single subject 3C O-1 Y Y Y Y
R-2
5.1 Each BDIR shall contain at least one or more 2D image and zero or more geometric 3C M Y Y Y Y
R-3
representations (range images, 3D point maps, 3D vertex representations) of a human face.
5.1 2D image data will be encoded using JPEG, JPEG2000 or PNG. 3C O-1 Y Y Y Y
R-4
5.1 With the exception of the Format Identifier and the Version Number for the standard, which are 3C O-1 Y Y Y Y
R-5
null-terminated ASCII character strings, all data is represented in binary format.
5.1 There are no record separators or field tags; fields are parsed by byte count. 3C O-1 Y Y Y Y
R-6
6 ©ISO/IEC 2014 – All rights reserved
---------------------- Page: 9 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
5.1 The organization of the record format is as follows: 3C O-1
- A fixed-length (17 byte) General Header containing information about the overall
record, including the number of facial images represented and the overall record length
in bytes.
- A Representation block for each facial representation. This data consists of a
Representation Header and the Representation Data.
- The Representation Header consists of
• A fixed length (19 bytes) common elements defined in ISO/IEC 19794-1:2011
• Multiple (including none) fixed length (5 byte) Quality blocks describing the quality of
the representation.
• A fixed length (17 byte) Facial Information block describing discernable characteristics Y Y Y Y
R-7
of the subject such as gender.
• Multiple (including none) fixed length (8 byte) Landmark Point blocks describing
Landmark Points in a facial image.
• A fixed length (11 byte) Image Information block describing digital properties of the
image such as Face Image Type and dimensions such as width and height.
- The Representation Data consists of
• Image data consisting of a JPEG, JPEG2000 or PNG encoded data block.
• For Face Image Types containing 3D information a 3D Information block (95 byte)
describing properties of this data.
• For Face Image Types containing 3D information the 3D Data block describing the 3D
shape of the face.
5.1 Multiple 2D / 3D representations of the same biometric data subject can be described in a single 3C O-1
Y Y Y Y
R-8
record. This is accomplished by including multiple representation blocks after the General
Header block.
5.1 Representation blocks containing 2D data can be stored together with Representation blocks 3C O-1 Y Y Y Y
R-9
also containing 3D data.
5.2.1 Within the record format and all well-defined data blocks therein, all multi-byte quantities are 1 M Y Y Y Y
R-10
stored in Big-Endian format.
R-11 5.2.2 All numeric values are fixed-length unsigned integer quantities, unless otherwise specified. 3C O-1 Y Y Y Y
R-12 5.2.3 The conversion of a numeric value to integer is given by rounding down if the fractional portion 3C O-1 Y Y Y Y
is less than 0,5 and rounding up if the fractional value is greater than or equal to 0,5.
©ISO/IEC 2014 – All rights reserved 7
---------------------- Page: 10 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
5.2.4 the following fields are mandatory, but the value of the field can indicate that the field is 3C O-1
unspecified: Capture Device Technology Identifier, Capture Device Vendor Identifier, Capture
Device Type Identifier, Gender, Eye Colour, Hair Colour, Subject Height, Property, Expression,
R-13 Y Y Y Y
Pose Angle, Pose Angle Uncertainty, Image Colour Space, 3D Capture Device Technology
Identifier, 3D Capture Device Vendor Identifier, 3D Capture Device Type Identifier, 3D to 2D
Image Temporal Synchronicity, 3D to 2D Texture Temporal Synchronicity, 3D Acquisition Time,
2D Texture Acquisition Time, Texture Map Type, and Texture Map Spectrum.
5.2.5 A field value labelled by the identifier “Unknown” shall be used to denote that the information 3C O-1 Y Y Y Y
R-14
encoded by the field cannot be determined by examination of the face image.
5.3.1 The General Header block consists of seven fields: Format Identifier, Version Number, Length 3C O-1
R-15 Y Y Y Y
of Record, Number of Representations, Capture Device Vendor Identifier, Capture Device Type
Identifier and the Temporal Semantics field as shown in Table 2.
R-16 5.3.2 The format identifier shall be recorded in four bytes. 1 M Y Y Y Y
R-17 5.3.2 The format identifier shall consist of three characters "FAC" followed by a zero byte as a NULL 1 M Y Y Y Y
string terminator.
R-18 5.3.3 The number for the version of ISO/IEC 19794-5 used for constructing the BDIR shall be placed 1 M Y Y Y Y
in four bytes.
5.3.3 This version number shall consist of three ASCII numerals followed by a zero byte as a NULL 1 M
string terminator.
R-19 Y Y Y Y
The first and second character will represent the major version number and the third character
will represent the minor revision number. The Version Number of ISO/IEC 19794-5:2010 shall
be 30333000 ; “030” – Version 3 revision 0.
HEX
R-20 5.3.4 The length (in bytes) of the entire BDIR shall be recorded in four bytes. 1 M Y Y Y Y
R-21 5.3.4 This count shall be the total length of the BDIR including the general record header and one or 2 M Y Y Y Y
more representation records.
R-22 5.3.5 The total number of representation records contained in the BDIR shall be recorded in two 1, 2 M Y Y Y Y
bytes.
R-23 5.3.5 A minimum of one representation is required. 1 M Y Y Y Y
8 ©ISO/IEC 2014 – All rights reserved
---------------------- Page: 11 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
R-24 5.3.6 Certification Flag 1 M Y Y Y Y
The value shall be 00 .
HEX
R-25 5.3.7 Temporal Semantics 1 M Y Y Y Y
This two byte (2 byte) field shall be assigned according to Table 3.
5.3.7 This supports storage of multiple representations: from a single session (e.g. from a photo 3C O-1
R-26 Y Y Y Y
shoot); from distinct sessions (e.g. from cash dispenser transactions); and from a temporal
sequence (e.g. a video sequence of equally time-spaced representations).
5.4.1 The Representation Header 3C O-1
R-27 Structure Y Y Y Y
The Representation Header is intended to describe discrete properties of the individual
discernable from the image, one is included for each facial representation included in the record.
5.4.1 The Representation Header consists of the Representation Length, the Capture Date and Time, 3C O-1
the Capture Device Technology Identifier, the Capture Device Vendor Identifier. These are
R-28 Y Y Y Y
followed by the Number of Quality Blocks field and the related number of Quality blocks. Finally
the Representation Header contains the Facial Information block, the optional multiple
Landmark Point blocks, and the Image Information block.
5.4.2 Representation Length 1, 2 M
R-29 Y Y Y Y
The (4 byte) Representation Length field denotes the length in bytes of the representation
including the representation header fields.
5.4.2 The minimum value of the Representation Length is 51 bytes, consisting of a minimum 47 bytes 1 M
R-30 Y Y Y Y
for the Representation Header plus the size of the Representation Data, i.e. minimum 4 bytes
for the Length of Image Data Block field assuming 0 bytes for the variable data.
5.4.3 Capture Date and Time 3C O-1
R-31 Y Y Y Y
The capture date and time field shall indicate when the capture of this representation started in
Coordinated Universal Time (UTC).
R-32 5.4.3 The capture date and time field shall consist of 9 bytes. 1 M Y Y Y Y
R-33 5.4.3 Its value shall be encoded in the form given in ISO/IEC 19794-1. 1 M Y Y Y Y
R-34 5.4.4 Capture Device Technology Identifier 1 M Y Y Y Y
Capture device technology Identifier shall be encoded in one byte.
©ISO/IEC 2014 – All rights reserved 9
---------------------- Page: 12 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
R-35 5.4.4 This field shall indicate the class of device technology used to acquire the captured biometric 3C O-1 Y Y Y Y
sample.
5.4.4 Many different types of capture devices work in the visible spectrum or in near infra-red (NIR). 3C O-1
R-36 Y Y Y Y
To indicate that the capture device operates in NIR the highest bit in the Capture Device
Technology Identifier field shall be set to 1.
5.4.4 See Table 4 for the enumerated list of possible values.
Table 4 — Capture Device Technology Identifier codes
Description Value
Unknown or Unspecified 00
HEX
Static photograph from an unknown source 01
HEX
Static photograph from a digital still-image
02
HEX
camera
R-37 Y Y Y Y
1 M
Static photograph from a scanner 03HEX
Video frame(s) from an unknown source 04
HEX
Video frame(s) from an analogue video camera 05
HEX
Video frame(s) from a digital video camera 06
HEX
Reserved by SC37 for future use 07 to 7F
HEX HEX
Vendor specific 80 to FF
HEX HEX
5.4.5 Capture Device Vendor Identifier 1 M
R-38 Y Y Y Y
The (2 byte) Capture Device Vendor Identifier shall identify the biometric organisation that owns
the product that created the BDIR.
R-39 5.4.5 The capture device algorithm vendor identifier shall be encoded in two bytes carrying a CBEFF 3C O-1 Y Y Y Y
biometric organization identifier (registered by IBIA or other approved registration authority).
R-40 5.4.5 A value of all zeros shall indicate that the capture device vendor is unreported. 1 M Y Y Y Y
R-41 5.4.6 Capture Device Type Identifier 1 M Y Y Y Y
The (2 byte) Capture Device Type Identifier shall identify the product type that created the BDIR.
10 ©ISO/IEC 2014 – All rights reserved
---------------------- Page: 13 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
R-42 5.4.6 It shall be assigned by the registered product owner or other approved registration authority. 3C M Y Y Y Y
5.4.6 A value of all zeros shall indicate that the capture device type is unreported. 1 M Y Y Y Y
R-43
R-44 5.4.6 If the capture device vendor identifier is 0000 , then also the capture device type identifier 2 M Y Y Y Y
HEX
shall be 0000
HEX
R-45 5.4.7 Number of Quality Blocks 2 M Y Y Y Y
This field is followed by the number of 5 byte Quality blocks reflected by its value.
R-46 5.4.7 A value of zero (0) means that no attempt was made to assign a quality score. In this case, no 2 M Y Y Y Y
Quality blocks are present.
5.4.8 Quality Score 1, 3C M
R-47 Y Y Y Y
The (1 byte) Quality Score, as defined in ISO/IEC 29794-1, shall be a quantitative expression of
the predicted verification performance of the biometric sample.
R-48 5.4.8 Valid values for Quality Score are integers between 0 and 100, where higher values indicate 1 M Y Y Y Y
better quality.
R-49 5.4.8 A value of 255 is to handle a special case. 1 M Y Y Y Y
R-50 5.4.8 An entry of 255 shall indicate a failed attempt to calculate a quality score. 3C O-1 Y Y Y Y
5.4.9 Quality Algorithm Vendor Identifier 1 M
R-51 To enable the recipient of the quality score to differentiate between quality scores generated by Y Y Y Y
different algorithms, the provider of quality scores shall be uniquely identified by this two-byte
field.
R-52 5.4.9 This is registered with the IBIA or other approved registration authority. 3C O-1 Y Y Y Y
5.4.10 Quality Algorithm Identifier 1 M
R-53 Y Y Y Y
The (2 byte) Quality Algorithm Identifier specifies an integer product code assigned by the
vendor of the quality algorithm.
R-54 5.4.10 It indicates which of the vendor’s algorithms (and version) was used in the calculation of the 1 M Y Y Y Y
quality score and should be within the range 1 to 65 535.
©ISO/IEC 2014 – All rights reserved 11
---------------------- Page: 14 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
5.4.10 Table 5 summarizes the quality field. All values are fixed-length unsigned integer quantities 1, 3C M
represented in Big-Endian format.
Table 5 — Structure of Quality blocks
Valid
Description Length Note
values
This field is followed by the number of 5-byte
Quality Blocks reflected by its value.
Number of Quality Blocks 1 byte [0,255] A value of zero (0) means that no attempt was
made to assign a quality score. In this case, no
Quality Blocks are present.
0: lowest
Y Y Y Y
[0,100]
R-55
Quality Score 1 byte 100: highest
255
255: failed attempt to assign a quality score
Quality Algorithm Vendor Identifier shall be
registered with IBIA or other approved registration
Quality algorithm
2 bytes [1,65535] authority as a CBEFF biometric organization. Refer
vendor Identifier
CBEFF vendor Identifier registry procedures in
ISO/IEC 19785-2.
Quality Algorithm Identifier may be optionally
registered with IBIA or other approved registration
Quality algorithm
2 bytes [1,65535] authority as a CBEFF Product Code. Refer to
Identifier
CBEFF product registry procedures in ISO/IEC
19785-2.
5.5.1 The Facial Information Block 3C O-1
Structure
R-56 Y Y Y Y
The Facial Information Block consists of the Number of Landmark Points, the Gender, the Eye
Colour, the Hair Colour, the Subject Height, the Property Mask, the Expression Mask, the Pose
Angle, and the Pose Angle Uncertainty fields.
5.5.2 Number of Landmark Points 1, 2 M
R-57 Y Y Y Y
The (2 byte) Number of Landmark Points field shall be the number of Landmark Point blocks
that follow the Facial Information block.
12 ©ISO/IEC 2014 – All rights reserved
Quality Block
---------------------- Page: 15 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
5.5.3 Gender 1, 3C M
The (1 byte) Gender field shall represent the gender of the subject according to Table 6.
Table 6 — Gender codes
Description Value
R-58 Y Y Y Y
Unspecified 00
HEX
Male 01
HEX
Female 02
HEX
Unknown FF
HEX
5.5.4 Eye Colour 1, 3C M
The (1 byte) Eye Colour field shall represent the colour of irises of the eyes according to
Table 7.
Table 7 — Eye Colour codes
Description Value
Unspecified 00
HEX
Black 01
HEX
Blue 02
HEX
R-59 Y Y Y Y
Brown 03
HEX
Gray 04
HEX
Green 05
HEX
Multi-Coloured 06
HEX
Pink 07
HEX
Reserved by SC 37 for future use 08HEX to FEHEX
Other or Unknown (e.g. cannot be determined from
FF
HEX
image, monochrome image)
R-60 5.5.4 If the eyes are different colours, then the right eye colour is to be encoded. 3C O-1 Y Y Y Y
©ISO/IEC 2014 – All rights reserved 13
---------------------- Page: 16 ----------------------
ISO/IEC 19794-5:2011/Amd.1:2014
Subformat
Ref. in
Requirement IUT Supported Test
Applicability
main Requirement Summary Level Status
ID Support Range Result
body P
B F T
5.5.5 Hair Colour 1, 3C M
The (1 byte) Hair Colour field shall represent the colour of the hair according to Table 8.
Table 8 — Hair Colour codes
Description Value
Unspecified 00
HEX
Bald 01
HEX
Black 02
HEX
R-61 Y Y Y Y
Blonde 03
HEX
Brown 04
HEX
Gray 05
HEX
White 06
HEX
Red 07
HEX
Reserved by SC 37 for future use 08 to FE
HEX HEX
Unknown or Other FF
HEX
5.5.6 Subject Height 1, 3C M
The (1 byte) Subject Height field shall represent the height of the subject according to Table 9.
Table 9 — Subject Height codes
R-62 Y Y Y Y
Description Value
Unspecified 00
HEX
Subject Height in cm 01 to FF
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.