SIST-TS CEN/TS 16428:2013

SLOVENSKI STANDARD
SIST-TS CEN/TS 16428:2013
01-januar-2013
0HGREUDWRYDOQRVWELRPHWULþQLKSURILORY1DMEROMãHSUDNVH]D]DMHPHGHVHWSUVWQLK
RGWLVRYGODQL
Biometrics Interoperability profiles - Best Practices for slap tenprint captures
Profile für biometrische Interoperabilität - Optimales Vorgehen bei Erfassung aller Finger
mittels gleichzeitigem Auflegen
Interopérabilité des profils biométriques - Recommandations pour la capture de dix
empreintes digitales à plat
Ta slovenski standard je istoveten z: CEN/TS 16428:2012
ICS:
35.240.15 Identifikacijske kartice in Identification cards and
sorodne naprave related devices
SIST-TS CEN/TS 16428:2013 en,fr,de
2003-01.Slovenski inštitut za standardizacijo. Razmnoževanje celote ali delov tega standarda ni dovoljeno.

---------------------- Page: 1 ----------------------

SIST-TS CEN/TS 16428:2013

---------------------- Page: 2 ----------------------

SIST-TS CEN/TS 16428:2013


TECHNICAL SPECIFICATION
CEN/TS 16428

SPÉCIFICATION TECHNIQUE

TECHNISCHE SPEZIFIKATION
October 2012
ICS 35.240.15
English Version
Biometrics Interoperability profiles - Best Practices for slap
tenprint captures
Interopérabilité des profils biométriques - Profile für die biometrische Interoperabilität - Optimales
Recommandations pour la capture de dix empreintes Vorgehen bei Erfassung aller Finger mittels gleichzeitigem
digitales à plat Auflegen
This Technical Specification (CEN/TS) was approved by CEN on 27 August 2012 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, Slovakia, Slovenia, Spain, Sweden, Switzerland, Turkey and United
Kingdom.





EUROPEAN COMMITTEE FOR STANDARDIZATION
COMITÉ EUROPÉEN DE NORMALISATION

EUROPÄISCHES KOMITEE FÜR NORMUNG

Management Centre: Avenue Marnix 17, B-1000 Brussels
© 2012 CEN All rights of exploitation in any form and by any means reserved Ref. No. CEN/TS 16428:2012: E
worldwide for CEN national Members.

---------------------- Page: 3 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
Contents Page
Foreword .3
1 Scope .4
2 Sensor hardware requirement .5
3 Acquisition software .5
4 Logging and evaluation of data .7
5 Operational process .9
6 Operational issues . 12
Annex A (informative) Example of acquisition process . 15
Annex B (informative) Example of an acquisition process based on composite records . 16
Annex C (informative) Example of a quality metric for the acquisition process . 19
Bibliography . 20

2

---------------------- Page: 4 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
Foreword
This document (CEN/TS 16428:2012) 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 [and/or CENELEC] 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, Slovakia, Slovenia, Spain, Sweden, Switzerland, Turkey and the United Kingdom.
3

---------------------- Page: 5 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)

1 Scope
The main goal of this Technical Specification is to give guidelines to follow during the acquisition process of
slap tenprints in order to obtain fingerprints with the best quality possible in acceptable time constraints.
NOTE Non-cooperative users are out of the scope of this Technical Specification.
When using ten-fingerprint sensors, it is fundamental to know how to use them and how to proceed during the
acquisition. This Technical Specification describes how to capture fingerprints correctly by specifying best
practices for slap ten-print captures.
This Technical Specification gives guidance on the following topics:
1) Recommendations on the hardware of the fingerprint sensor and its deployment,
2) Recommendations on user guidance,
3) Recommendations on the enrolment process including a sample workflow,
4) Recommendations for developers and system integrators on application software,
5) Recommendations on processing, compression and coding of the acquired fingerprint images,
6) Recommendations on operational issues and data logging,
7) Recommendations on the evaluation of a solution and its components.
Although this Technical Specification primarily focuses on reaching optimal data quality for enrolment
purposes, the recommendations given here are applicable for other purposes. All processes which rely on
good quality tenprint slaps can take advantage of the best practices reported here.
4

---------------------- Page: 6 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
2 Sensor hardware requirement
Image quality should comply with the quality specifications from ISO/IEC 19794-4:2011 [1]. EBTS/F
corresponds to Annex B.1 and BSI TR-03121 corresponds to Annex B.3 of ISO/IEC 19794-4:2011 [1].
NOTE 1 This Technical Specification considers optical sensors based on the principle of total internal reflection.
However, this does not mean that other technologies cannot be used for tenprint enrolment purposes. As soon as
sufficient experiences are available and recommendations can be given on emerging technologies, they will be included in
a future version of this document.
The sensor device should provide methods for re-calibration in the field by qualified service staff if the device
technically supports it.
It is recommended that the compliance of a sensor device to the applicable quality standard can be verified at
any time in the operational environment.
NOTE 2 The need for calibration or re-calibration depends on the sensor technology and calibration might not be
necessary for all devices.
3 Acquisition software
3.1 Acquisition process
For the acquisition process, the highest quality images should be used. The acquisition of these images
should be done automatically. The sequence of images having the highest quality should be used; if a timeout
has occurred then these may be below the desired quality levels.
An example for an acquisition process design can be found in Annexes A and B, an example for a quality
metric can be found in Annex C.
3.2 User feedback
The presence of a user interface is strongly advised to give feedback to the user.
Feedback can be given, for example, by:
 A screen attached in close neighbourhood to the sensor,
 Illuminated pictograms on the sensor,
 LED’s assigned to pictograms directly on the sensor.
The following information should be given to the user:
 Assistance to finger positioning with images and/or video on the screen and/or audio instructions (for
instance to instruct the user to move its fingers to the left/right/top/bottom),
 Visual and/or audio notification when a successful acquisition has been completed,
 A Quality indicator for each acquisition. This indicator should be simple, for example a two-state logic
(not good/good) or similar,
 If possible, the reason for a bad quality acquisition (e.g. wrong positioning of the hand).
5

---------------------- Page: 7 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
Additional information (e.g. a poster or a video) can be used to illustrate to users how to use the system. This
information can be displayed close to the sensor and additionally in the waiting zone.
Operators should be trained to give guidance to the users.
3.3 Acquisition check
The software linked to the sensor should take account of the following during the acquisition process in order
to perform a better acquisition:
 Any feedback provided by the sensor software (background correction, quality evaluation, end of
acquisition, etc.),
 A timeout for capturing the best available image in case the specified quality threshold is not
reached,
 The inability of the subject to provide a full set of fingerprints. Acceptable images for certain fingers
may not have been captured. This can be due to
 missing fingers,
 inability for the subject to interact with the sensor correctly,
 temporary or permanent issues with the subject’s fingerprints.
 The image quality of the captured images. This is to enable the system to finish the acquisition
process after the preset quality level or a timeout has been reached,
 The subject’s fingers have been removed from the sensor at the end of the acquisition process,
 All two consecutively captured slaps and captured thumbs are not identical. A duplicate check should
also be performed to ensure that all expected fingers have been captured once and once only,
NOTE Due to computational time constraints this recommendation could also be enforced by the operator instead of
the software.
 Residual traces have not been acquired,
 The fingerprint images are as originally acquired. Optionally, segmented images can be produced,
 Hand inversion between left and right slap has not occurred. This check can be based on the
different physical characteristics of the shapes of both hands.
3.4 Image processing
3.4.1 Segmentation
Independently of physical resolution of the sensor and the image acquired, the resolution of the fingerprint
image should be at least 197 ppcm (500 ppi) and, therefore, can differ from the scan resolution.
Depending on the call to capture one, two, three or four fingerprints, this number of individual fingerprints
should be extracted from the input image and provided as single fingerprints generated by a segmentation
process which takes into account fingers reported to be missed.
6

---------------------- Page: 8 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
For this segmentation process, the following criteria should be fulfilled:
 Ability to accept rotated fingerprints having the same direction in an angle up to 45°
 Rotated fingerprints having the same direction should be corrected to be vertical
 Segment the first part over the finger (first phalanx)
 Segmentation should be performed on uncompressed data.
Recommended size for fingerprint images is given in ISO/IEC 19794-4:2011, D.1.
NOTE Size limitation is done in order to prevent performance issues.
3.4.2 Compression
Fingerprint images should be compressed according to the recommendations in ISO/IEC 19794-4:2011,
section 8.3.17 “Image compression algorithm”.
NOTE 1 The compression ratio should not be too high, a maximum compression ratio of 15 is recommended.
NOTE 2 The WSQ compression is mainly used for fingerprint compression; it has been optimized to be compatible with
minutiae calculation.
The implementation of the used WSQ algorithm should be certified by the FBI and should be referenced by
the respective certificate number (coded in the WSQ header).
Multiple lossy compressions should be avoided as they harm image quality.
4 Logging and evaluation of data
4.1 General
Logging and evaluation data might be subject to European Union or national legal constraints and should be
handled accordingly.
4.2 Logging data
The purpose of the logging data is not to track people but to give guidance to the staff in charge of the
enrollment and to maintain a constant quality of the acquisition process.
The following data, or parts of it, should be logged:
 Transaction ID
 Timestamp of acquisition
 Duration of biometric acquisition process
 Number of captured images
 Number of successful captures
 Quality scores for all captured fingerprints
 Overall quality score of captured slap or ten prints sets (if present)
7

---------------------- Page: 9 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
 Information about vendor, software, hardware and versions
 Information about the origin (e.g. Agency Identifier)
 Information about errors (e.g. about uniqueness check, segmentation, etc)
 Size of acquired data
 Testing flags (if applicable)
 Demographic data on the subject (gender, age).
NOTE It might be appropriate to have a regular logging workflow and an evaluation mode logging workflow with more
comprehensive logging data. The latter one could be used for regular or incident-based checks of the whole process.
When used in a verification or identification scenario, it is recommended to also log results of the verification
and identification process.
4.3 Useful statistical evaluations
Conducting regular (e.g. every month, every three month, every year) evaluations on the acquired logging
data is recommended.
As a minimum, the following basic set of evaluations should be conducted:
 Quality scores distribution
 Error code distribution
 Average enrolment duration
 Distribution of enrolment duration
 Distribution of gender and age, especially in relation to quality scores
When used in a verification or identification scenario, it is recommended to also evaluate the accumulated
results of the verification or identification attempts.
8

---------------------- Page: 10 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
5 Operational process
5.1 General user guidance
The presence of a user interface is strongly advised to support better acquisition.
The following placement recommendations should be applied:
 The user should set down the fingers flat on the sensor and in particular their tips but not set down
only the tips (see Figure 1) or the sides of the fingers (see Figure 2).


Figure 1 — Tips of the fingers Figure 2 — Sides of the finger
 The user should position his fingers straight, parallel to the edges of the sensor (see Figure 3) and
avoid any rotation unless a rotation is the only way to place all fingers on the acquisition surface of
the sensor (see Figure 4).


Figure 3 — Prefer parallel fingers in relation to Figure 4 — Avoid rotated fingers in relation to the
the edges edges
9

---------------------- Page: 11 ----------------------

SIST-TS CEN/TS 16428:2013
CEN/TS 16428:2012 (E)
 The user should position the thumb(s) straight, parallel to the edges of the sensor (see Figure 5) and
avoid any rotation.


Figure 5 — Correct thumbs position Figure 6 — Wrong thumbs position
 The user should put down all the fingers simultaneously on the sensor (do not roll them on the
sensor or do not put down one finger after the other on the sensor)
 The user should not spreading fingers too much (see Figure 7) and cross his fingers (see Figure 8)


Fi
...