SIST-TS CEN/TS 17051:2017
(Main)Full body photography
Full body photography
This Technical Specification is intended to provide a Full Body Image Format for pattern recognition services and applications requiring the exchange of full body image data. Its typical applications include:
a) human examination of high resolution full body images;
b) human verification of identity based on full body images;
c) computer automated full body identification;
d) computer automated full body verification.
To enable applications on a wide variety of devices, including devices that have limited data storage, and to improve image recognition accuracy, ISO/IEC 19794 standards are followed regarding not only data format, but also scene constraints (lighting, pose, expression, etc.), photographic properties (positioning, camera focus, etc.), and digital image attributes (image resolution, image size, etc.).
A specific biometric profile for cross-border interoperability is required for full body photographs. Full body photography standardization is required to get good quality database images for identification and verification using video surveillance and other similar system generated images. At the moment, border guards take full body photographs using local practices for enrolment, verification, identification and watch list identification.
ISO 22311:2012 [10] specifies a common output file format that can be extracted from the video-surveillance contents collection systems to perform necessary processing. ISO/IEC 30137 [8] specifies data formats for storing, recording and transmitting biometric information acquired via a video surveillance system. The EN 62676 series [11] defines video surveillance systems for use in security applications.
The purpose of this Technical Specification is to provide expert guidance (i.e. best practices) for the photography of full body, especially when the resulting images are to be used for purposes of identification and verification, either by automated recognition systems or by human viewers.
Ganzkörperfotografie
Photographie du corps entier
Fotografija celega telesa
Ta tehnična specifikacija je namenjena zagotavljanju formata slike celega telesa za storitve in aplikacije za prepoznavanje vzorcev, pri katerih je potrebna izmenjava podatkov o sliki celega telesa. Običajni načini uporabe vključujejo:
a) človeški pregled visokoločljivostnih slik celega telesa;
b) človeško preverjanje identitete na podlagi slik celega telesa;
c) računalniško avtomatizirano prepoznavanje celega telesa;
d) računalniško avtomatizirano preverjanje celega telesa;
Za omogočanje uporabe prek številnih naprav, vključno z napravami z omejenim prostorom za shranjevanje podatkov, in za izboljšanje natančnosti prepoznavanja slik je treba upoštevati standarde ISO/IEC 19794 ne le glede formata podatkov, ampak tudi glede omejitev prizora (osvetlitev, položaj, izraz itd.), lastnosti fotografiranja (določanje položaja, fokus kamere itd.) in atributov digitalnih slik (ločljivost slike, velikost slike itd.).
Za fotografije celega telesa je potreben poseben biometrični profil za izvozno medobratovalnost. Standardizacija fotografije celega telesa je potrebna za pridobivanje slik za zbirko podatkov dobre kakovosti za identifikacijo in preverjanje z video nadzorom in drugimi podobnimi sistemsko ustvarjenimi slikami. Trenutno mejni policisti fotografirajo celo telo s pomočjo lokalnih praks za vpis, preverjanje, identifikacijo in identifikacijo na seznamu opazovanih oseb.
Standard ISO 22311:2012 [10] določa skupno izhodno obliko zapisa datoteke, ki jo je mogoče pridobiti iz zbirnih sistemov video nadzornih vsebin za izvajanje potrebne obdelave. Standard ISO/IEC 30137 [8] določa podatkovne formate za shranjevanje, snemanje in prenašanje biometričnih informacij, pridobljenih prek video nadzornega sistema. Skupina standardov EN 62676 [11] določa video nadzorne sisteme za varnostne aplikacije.
Namen te tehnične specifikacije je zagotoviti strokovne smernice (tj. najboljše prakse) za fotografiranje celega telesa, zlasti kadar se bodo nastale slike uporabljale za namene identifikacije in preverjanja z avtomatiziranimi sistemi za prepoznavanje ali osebnimi pregledi.
General Information
Standards Content (Sample)
SLOVENSKI STANDARD
SIST-TS CEN/TS 17051:2017
01-september-2017
Fotografija celega telesa
Full body photography
Ganzkörperfotografie
Photographie du corps entier
Ta slovenski standard je istoveten z: CEN/TS 17051:2017
ICS:
35.240.15 ,GHQWLILNDFLMVNHNDUWLFHýLSQH Identification cards. Chip
NDUWLFH%LRPHWULMD cards. Biometrics
SIST-TS CEN/TS 17051:2017 en,fr,de
2003-01.Slovenski inštitut za standardizacijo. Razmnoževanje celote ali delov tega standarda ni dovoljeno.
---------------------- Page: 1 ----------------------
SIST-TS CEN/TS 17051:2017
---------------------- Page: 2 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051
TECHNICAL SPECIFICATION
SPÉCIFICATION TECHNIQUE
May 2017
TECHNISCHE SPEZIFIKATION
ICS 35.240.15
English Version
Full body photography
Photographie du corps entier Ganzköperfotografie
This Technical Specification (CEN/TS) was approved by CEN on 6 February 2017 for provisional application.
The period of validity of this CEN/TS is limited initially to three years. After two years the members of CEN will be requested to
submit their comments, particularly on the question whether the CEN/TS can be converted into a European Standard.
CEN members are required to announce the existence of this CEN/TS in the same way as for an EN and to make the CEN/TS
available promptly at national level in an appropriate form. It is permissible to keep conflicting national standards in force (in
parallel to the CEN/TS) until the final decision about the possible conversion of the CEN/TS into an EN is reached.
CEN members are the national standards bodies of Austria, Belgium, Bulgaria, Croatia, Cyprus, Czech Republic, Denmark, Estonia,
Finland, Former Yugoslav Republic of Macedonia, France, Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania,
Luxembourg, Malta, Netherlands, Norway, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, Sweden, Switzerland,
Turkey and United Kingdom.
EUROPEAN COMMITTEE FOR STANDARDIZATION
COMITÉ EUROPÉEN DE NORMALISATIO N
EUROPÄISCHES KOMITEE FÜR NORMUN G
CEN-CENELEC Management Centre: Avenue Marnix 17, B-1000 Brussels
© 2017 CEN All rights of exploitation in any form and by any means reserved Ref. No. CEN/TS 17051:2017 E
worldwide for CEN national Members.
---------------------- Page: 3 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
Contents Page
European foreword . 4
Introduction . 5
1 Scope . 6
2 Normative reference . 6
3 Terms and definitions . 6
4 Abbreviated terms . 7
5 Conformance . 8
6 Data structures. 8
6.1 Body Tree concept . 8
6.2 Camera images . 8
6.3 Metadata . 9
6.3.1 General . 9
6.3.2 Pose Angle – Yaw . 9
6.3.3 Pose angle encoding . 10
7 Recommendations for Full Body Photography Systems . 11
7.1 Architecture . 11
7.2 Usability and accessibility. 11
7.3 Practical applications . 11
7.4 Photograph sets . 12
7.4.1 General . 12
7.4.2 Gait recognition . 12
7.4.3 Image recognition . 14
8 Full body photography . 14
8.1 Full body image technical requirements . 14
8.1.1 General . 14
8.1.2 Example full body photographs . 14
8.2 Full body photography session . 16
8.2.1 Typical workflow for full body photography session . 16
8.2.2 Full body photograph content requirements. 17
9 Photo studio recommendations for full body photography . 17
9.1 General . 17
9.2 Recommended camera orientation . 18
9.3 Recommended positioning and distance between camera and subject . 18
9.4 Recommended focusing settings . 19
9.5 Recommended white balance settings . 19
9.6 Recommended backdrop design . 19
9.6.1 General . 19
9.6.2 Example configurations for a photo studio. 20
10 Photography Use Cases . 21
10.1 General . 21
10.2 Photographic System Baseline Use Cases . 21
2
---------------------- Page: 4 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
11 Image Acquisition Measurement Methods . 23
11.1 General . 23
11.2 Exposure metering at various spots on a subject . 24
11.3 Standard Test Chart Setup . 24
11.3.1 The ISO 12233 Test Chart . 25
11.3.2 Grey scale, colour checking and EN 61966-8 test charts . 26
11.4 Measurement preparations and analysis . 26
11.4.1 General . 26
11.4.2 Preparations . 27
11.4.3 Analysis . 27
11.4.4 Camera image dynamic range checking . 28
11.4.5 Lighting checking . 28
11.4.6 Background checking . 28
12 Summary . 29
Bibliography . 30
3
---------------------- Page: 5 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
European foreword
This document (CEN/TS 17051:2017) has been prepared by Technical Committee CEN/TC 224
“Personal identification, electronic signature and cards and their related systems and operations”, the
secretariat of which is held by AFNOR.
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. CEN shall not be held responsible for identifying any or all such patent rights.
According to the CEN/CENELEC Internal Regulations, the national standards organisations of the
following countries are bound to announce this Technical Specification: Austria, Belgium, Bulgaria,
Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, Former Yugoslav Republic of Macedonia,
France, Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta,
Netherlands, Norway, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, Sweden, Switzerland,
Turkey and the United Kingdom.
4
---------------------- Page: 6 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
Introduction
Most countries around the world are provided with identification systems for law enforcement and
border control. Many of these systems are not limited to face recognition purposes. To be consistent in
such deployments and processes, technical documents, guidelines and best practice recommendations
are being developed by different groups. However, these documents are primarily focused on travel
document systems and the technical and operational issues to be considered when planning and
deploying such systems in Europe. Full body recognition is the biometric mode used as a secondary
mode in addition to face recognition or for forensic purposes. Face recognition is the biometric mode
suited to the practicalities of travel documents.
There is little guidance covering the full body imaging for cross-border interoperability or law
enforcement services. There is a need for guidance for the use of high quality digital cameras and video
surveillance devices for full body photography. This Technical Specification is not restricted to body
image data. For example, it may be possible to extract iris images in some scenarios where high
resolution cameras are used or body silhouette data for gait recognition when low resolution cameras
are in use.
5
---------------------- Page: 7 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
1 Scope
This Technical Specification is intended to provide a Full Body Image Format for pattern recognition
services and applications requiring the exchange of full body image data. Its typical applications
include:
a) human examination of high resolution full body images;
b) human verification of identity based on full body images;
c) computer automated full body identification;
d) computer automated full body verification.
To enable applications on a wide variety of devices, including devices that have limited data storage,
and to improve image recognition accuracy, ISO/IEC 19794 standards are followed regarding not only
data format, but also scene constraints (lighting, pose, expression, etc.), photographic properties
(positioning, camera focus, etc.), and digital image attributes (image resolution, image size, etc.).
A specific biometric profile for cross-border interoperability is required for full body photographs. Full
body photography standardization is required to get good quality database images for identification
and verification using video surveillance and other similar system generated images. At the moment,
border guards take full body photographs using local practices for enrolment, verification, identification
and watch list identification.
ISO 22311:2012 [10] specifies a common output file format that can be extracted from the video-
surveillance contents collection systems to perform necessary processing. ISO/IEC 30137 [8] specifies
data formats for storing, recording and transmitting biometric information acquired via a video
surveillance system. The EN 62676 series [11] defines video surveillance systems for use in security
applications.
The purpose of this Technical Specification is to provide expert guidance (i.e. best practices) for the
photography of full body, especially when the resulting images are to be used for purposes of
identification and verification, either by automated recognition systems or by human viewers.
2 Normative reference
The following documents, in whole or in part, are normatively referenced in this document and are
indispensable for its application. For dated references, only the edition cited applies. For undated
references, the latest edition of the referenced document (including any amendments) applies.
EN 61966-8, Multimedia systems and equipment - Colour measurement and management - Part 8:
Multimedia colour scanners
ISO 12233, Photography — Electronic still picture imaging — Resolution and spatial frequency responses
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
3.1
biometric verification
process of confirming a biometric claim through biometric comparison
[SOURCE: ISO/IEC 2382-37]
6
---------------------- Page: 8 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
3.2
biometric identification
process of searching against a biometric enrolment database to find and return the biometric reference
identifier(s) attributable to a single individual
[SOURCE: ISO/IEC 2382-37]
3.3
CCTV
closed-circuit television
video surveillance
system that sends television signals to a limited number of screens or other receivers, and is often used
in shops and public places to prevent crime
3.4
4K
originally described digital cinema (4096 × 2160 px)
Note 1 to entry: Digital Cinema resolution is not often used in television, the term “4K” or “4K Ultra HD”
(3840 × 2160 px) was invented to achieve a 16 × 9 aspect ratio.
4 Abbreviated terms
ASN.1 Abstract Syntax Notation number One
CCTV closed-circuit television
CEN European Committee for Standardization
CIE International Commission on Illumination (Commission Internationale de l'Eclairage)
DCI Digital Cinema Initiatives consortium
DSLR Digital single-lens reflex camera
EU European Union
ICAO International Civil Aviation Organization
IEC International Electrotechnical Commission
ISO International Organization for Standardization
JTC Joint Technical Committee
MP4 digital multimedia file format used to store video and audio
NIST National Institute of Standards and Technology
RGB Red Green Blue colour representation
SD Standard-definition television
WG Working Group
7
---------------------- Page: 9 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
5 Conformance
Conformity with this document requires compliance with the record format specification defined in
Clause 6.
6 Data structures
6.1 Body Tree concept
A full body photography system produces photographs for human examination and for automated full
body verification and identification.
Figure 1 — Example of biometric features for various processes provided by full body images
and videos
Standard poses help the parsing of the body tree. Parsing can be done using methods utilizing
algorithms which process the human body as an assembly of parts. Segmentation can be used as a pre-
processing step.
6.2 Camera images
It is recommended to take pictures using vertical camera orientation. The original camera image is
saved whenever possible without any additional cropping, rotation or other image processing. The full
body pose shall be between 60 % and 90 % of the vertical length of the image. The whole body width
shall be visible. The margin area around the human figure shall be at least 5 % of the image height.
To satisfy the requirements for minimum image size, the normative practice shall be to fill any
undefined set of pixels with sRGB middle grey (128, 128, 128). This process does not refer to the filling
of the background along the body contour line, which shall be avoided in full body images. The middle
grey is a tone that is perceptually about halfway between black and white on a lightness scale. The use
of grey is based on the assumption that human viewer is less distracted by the image fringe area when
grey is used if compared to white or black borders. In the sRGB colour space used widely in monitors
and photography, CIELAB middle grey is equivalent to 46,6 % brightness. Middle grey is typically
defined as 18 % reflectance in visible light.
For a level-51 image capture profile, the minimum number of pixels in the digital image shall be 2400
pixels in the horizontal direction by 3200 pixels in the vertical direction. Off-the-shelf 8 megapixel
8
---------------------- Page: 10 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
digital cameras satisfy this requirement. Most robust mobile phones are capable of taking level 51 or
higher level images.
Level 50 image size is compatible with 4K video format as shown in Table 1. 4K is typically a landscape
format when both level-50 and level-51/52 has been defined as portrait formats.
Image orientation is generally not a problem as JPEG Exif (Exchangeable image file format) metadata
shows the camera orientation. MPEG-4 AVC/H.264 (ISO/IEC 14496-10 MPEG-4 Part 10, Advanced
Video Coding) implementations for video coding allow frame extraction for biometric sample
comparison processing to take place. MPEG-4 Part 14 or MP4 is a digital multimedia format most
commonly used to store video and audio. MPEG-4 Part 14 (formally ISO/IEC 14496-14:2003) is a
standard specified as a part of MPEG-4. MP4 is the related file format.
Table 1 — Comparison of image formats
Image format name (details) resolution aspect ratio pixels
Level-51/52 (profile) * 2400 × 3200 1:1.33 (3:4) 7,680,000
Level-50 (profile) * 3300 × 4400 1:1.33 (3:4) 14,520,000
DCI 4K (native resolution) 4096 × 2160 1,90:1 (19:10) 8,847,360
*ANSI/NIST has defined best practices for mugshots. These definitions are used as a baseline also for
full body images. For an ANSI/NIST level-50 [4] image capture profile, the minimum number of pixels in
the digital image shall be 3300 pixels in the horizontal direction by 4400 pixels in the vertical direction.
Off-the-shelf 15 (or more) megapixel digital cameras satisfy this requirement.
6.3 Metadata
6.3.1 General
It is required to include the pose angle as descriptive metadata. Pose angles are defined relative to the
frontal pose of the subject. See Figure 2 for the definition of the pose angle.
6.3.2 Pose Angle – Yaw
The yaw angle Y is the rotation in degrees about the y-axis (vertical axis) shown in Figure 2. Frontal
poses have a yaw angle of 0 degrees. Positive angles represent faces looking to their left (a counter-
clockwise rotation around the y-axis).
9
---------------------- Page: 11 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
Figure 2 —Definition of the yaw body pose angle. Pitch and Roll are not in use for the body
(0,0,0) (+45,0,0) (+90,0,0) (+135,0,0) (+180,0,0) (−135,0,0) (−90,0,0) (−45,0,0)
Figure 3 — Examples of pose angles applied for full body images in the same way as for facial
images
6.3.3 Pose angle encoding
Information exchange file in XML or ASN.1 format should contain proper pose angle data. Following
XML definition is similar to the Figure 3 facial image (−45,0,0) pose angle, image on the right:
< BodyInformation >
< PoseAngle >
< Yaw Uncertainty = ”0” > −45 < /Yaw >
< /PoseAngle >
< /BodyInformation >
Binary encoding enables the XML or ASN.1 usage in bandwidth or storage constrained environments.
10
---------------------- Page: 12 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
7 Recommendations for Full Body Photography Systems
7.1 Architecture
The aspects that could be considered by the definition of full body photography system architecture
are:
— biometric capture sub-process, carried out by a photographic capture unit;
— image formatting sub-process, carried out by a photographic application program;
— visualization of process and results, both for operator and the subject of biometric authentication
process;
— integrity of photography system;
— denial of service (system is supposed to be used only by authorized operator), what can be done
e.g. with biometric verification of operator;
— connection to other systems (databases, etc.) with the focus on protocols and the integrity of such
connection.
Only first two aspects are in the scope of this document. The other aspects are covered with the
documents in Bibliography and not in detail considered in this document.
7.2 Usability and accessibility
Accessible systems should be designed to be equitable in use for subjects who have permanent or
temporary physical or psychological inabilities. They should be easy to use and with a wide tolerance of
operation. For subjects that cannot use the biometric system alternative systems are necessary and
should be provided.
General guidance on these aspects is given in ISO/IEC/TR 24714-1:2008 [1]. Pictogram
recommendations can be found in ISO/IEC 24779 [8] standards.
7.3 Practical applications
In practice, full body images and walk through videos are taken from crime suspects and saved to
databases. The biometric capture process may involve a single biometric capture device (camera) or
several devices. Biometric features are extracted from high resolution samples. High resolution images
and 4K videos carry enough information for various biometric processes. Biometric reference is formed
as the stored biometric samples are attributed to a biometric data subject and used as the object of
biometric comparison.
Depending on the cultural requirements persons are photographed wearing clothing or near naked.
According to Interpol guidelines [2] photographic and video recording of bodies at the disaster site and
within the mortuary is important both for evidence and because it can help to establish the cause of the
incident.
State-of-the-art image recognition algorithms can be used to select images of people with almost no
useful identity information in the face. Recognition of the face alone in these cases are near chance level,
but recognition of the person based on larger part of the body is accurate, according to the research
work done at the University of Texas at Dallas [3]: “For twenty years, the assumption in the automatic
face recognition community has been that all important identity information is in the face. These results
should point us toward exploring new ways to improve automatic recognition.”
11
---------------------- Page: 13 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
Body images appear in video surveillance videos more often than clear face images. Faces and body
images are added to the watch lists from observation of behaviours in the video material. In order to
increase the international interoperability of the biometric samples, it was necessary to create a
standard describing the biometric sample formats for full body images.
SD video frame comparison with high quality reference images gives better results than comparing two
SD level images. At the moment 4K DSLRs capable of taking high resolution still images and 4K video
are available at a reasonable price. Video surveillance systems evolve from HD to 4K in the near future
and therefore the resolution level of still images should be high. A passport quality face image is
obtained by cropping the 4K full body frontal image of a person.
1
Data formats for biometrics in video surveillance systems (ISO/IEC 30137-3) [6] and high efficiency
coding (ISO/IEC 23008-12) [7] are standardized for data format integration work.
7.4 Photograph sets
7.4.1 General
The set of photographs shall include at least five photographs of the subject: (frontal, left full profile,
right full profile, left half profile and right half profile).
Gait recognition and full body recognition can be paired to form a multi-mode biometric process in
order to improve the performance of a biometric system. If the person's facial area is not visible or the
amount of pixels in a video surveillance or other security camera still image is too low then body
silhouette can be used for identification or verification purposes.
7.4.2 Gait recognition
A gait recognition silhouette is the image of a person represented as a solid shape of a single colour,
usually black. The edges of a silhouette match the outline of the subject. Gait recognition walk through
video recording is recommended to improve the performance of both gait recognition and full body
photometric recognition.
To ensure that the gait sequence captures the body movement in detail, it is recommended that the
sequence is captured at the rate of 30 frames per second. This is a typical frame rate used in gait
research databases such as the CMU MoBo database and USF HumanID gait database.
In order to capture all the details of a gait signature, minimum of one full gait cycle, i.e. two full steps,
shall be captured. Figure 4 illustrates the silhouettes of the phases of one full gait cycle.
1
In preparation.
12
---------------------- Page: 14 ----------------------
SIST-TS CEN/TS 17051:2017
CEN/TS 17051:2017 (E)
Key
a, b, e stance phases
b, d swing phases
Figure 4 — Illustration of the phases of a full gait cycle
Various automated methods have been developed for gait recognition. Some methods use the image
data as an input while others only use silhouettes. Also, automated methods can use either aligned
images or non-aligned images. The capture process should allow for any method to be used for
automated recognition, therefore the gait sequence should be captured with a stationary camera.
The side view is the most discriminative view of a gait sequence. The subject should be instructed to
walk on a straight line perpendicular to the camera line of sight as illustrated in Figure 5. When thread
mill is used for walking it is easier to maintain stationary view of the person in the middle of the fr
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.