ASTM E3115-17(2023)
(Guide)Standard Guide for Capturing Facial Images for Use with Facial Recognition Systems
Standard Guide for Capturing Facial Images for Use with Facial Recognition Systems
SIGNIFICANCE AND USE
4.1 The key factors that determine image quality for highly controlled facial images (for example: passports, police mugshots, drive motor vehicle, etc.) are well understood with respect to their use in automated FR systems and are a critical factor which directly affects the searching accuracy of the FR system.
4.2 Image quality also plays a major role in determining the extent to which a trained facial examiner is able to reach a conclusion as to whether two images containing faces are likely to be of the same person or not. This applies to either reviewing a FR system candidate result set or 1:1 image comparisons.
4.3 This guide provides guidance for the capture of facial images under controlled, semi-controlled, and uncontrolled scenarios for constraints which can be categorized into the following types of requirements:
4.3.1 Scene, refers to the content, subject and background in the image,
4.3.2 Photographic, refers to lighting, focus and other constraints required for image capture, and
4.3.3 Digital, refers to the conversion of the captured image into a digital record.
SCOPE
1.1 This guide is intended for use by practitioners who are choosing, setting up, and operating photographic equipment designed to capture facial images for use with an automated Facial Recognition System or used for manual comparisons by a trained facial examiner. This guide provides an overview of how to achieve the specifications defined in Annex E of ANSI/NIST-ITL-1-2011, Update 2015, for capturing facial images.
1.2 Annex E of ANSI/NIST-ITL-1-2011 defines a well-controlled capture environment and subject whereas this document will give guidance where tight controls in the capture environment and subject control cannot be achieved.
1.3 This guide addresses equipment considerations for two-dimensional (2D) conventional images. It does not address video, scanners, or three-dimensional (3D) capture.
1.4 The values stated in SI units are to be regarded as standard. The values given in parentheses are mathematical conversions to non-SI units that are provided for information only and are not considered standard.
1.5 This standard does not purport to address all of the safety concerns, if any, associated with its use. It is the responsibility of the user of this standard to establish appropriate safety, health, and environmental practices and determine the applicability of regulatory limitations prior to use.
1.6 This international standard was developed in accordance with internationally recognized principles on standardization established in the Decision on Principles for the Development of International Standards, Guides and Recommendations issued by the World Trade Organization Technical Barriers to Trade (TBT) Committee.
General Information
Relations
Standards Content (Sample)
This international standard was developed in accordance with internationally recognized principles on standardization established in the Decision on Principles for the
Development of International Standards, Guides and Recommendations issued by the World Trade Organization Technical Barriers to Trade (TBT) Committee.
Designation: E3115 − 17 (Reapproved 2023) An American National Standard
Standard Guide for
Capturing Facial Images for Use with Facial Recognition
Systems
This standard is issued under the fixed designation E3115; the number immediately following the designation indicates the year of
original adoption or, in the case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. A
superscript epsilon (´) indicates an editorial change since the last revision or reapproval.
1. Scope 2. Referenced Documents
2.1 ASTM Standards:
1.1 This guide is intended for use by practitioners who are
E2916 Terminology for Digital and Multimedia Evidence
choosing, setting up, and operating photographic equipment
Examination
designed to capture facial images for use with an automated
Facial Recognition System or used for manual comparisons by
2.2 Other Biometric Standards:
a trained facial examiner. This guide provides an overview of
ANSI/NIST-ITL-1-2011, Update 2015 Data Format for the
how to achieve the specifications defined in Annex E of
Interchange of Fingerprint, Facial and Other Biometric
ANSI/NIST-ITL-1-2011, Update 2015, for capturing facial
Information
images.
NIST Special Publication 500-280v2 Mobile ID Device Best
Practice Recommendation, Version 2.0
1.2 Annex E of ANSI/NIST-ITL-1-2011 defines a well-
controlled capture environment and subject whereas this docu-
ment will give guidance where tight controls in the capture 3. Terminology
environment and subject control cannot be achieved.
3.1 Definitions:
3.1.1 For terms relating to digital and multimedia evidence,
1.3 This guide addresses equipment considerations for two-
refer to Terminology E2916.
dimensional (2D) conventional images. It does not address
3.2 Definitions of Terms Specific to This Standard:
video, scanners, or three-dimensional (3D) capture.
3.2.1 fish eye effect, n—a type of distortion, where central
1.4 The values stated in SI units are to be regarded as
objects of the image erroneously appear closer than those at the
standard. The values given in parentheses are mathematical
edge typically resulting in what appear to be unusually large
conversions to non-SI units that are provided for information
noses in the image.
only and are not considered standard.
3.3 Acronyms:
1.5 This standard does not purport to address all of the
3.3.1 2D—two-dimensional
safety concerns, if any, associated with its use. It is the
3.3.2 FR—facial recognition
responsibility of the user of this standard to establish appro-
priate safety, health, and environmental practices and deter-
4. Significance and Use
mine the applicability of regulatory limitations prior to use.
1.6 This international standard was developed in accor-
4.1 The key factors that determine image quality for highly
dance with internationally recognized principles on standard- controlled facial images (for example: passports, police
ization established in the Decision on Principles for the
mugshots, drive motor vehicle, etc.) are well understood with
Development of International Standards, Guides and Recom-
respect to their use in automated FR systems and are a critical
mendations issued by the World Trade Organization Technical
factor which directly affects the searching accuracy of the FR
Barriers to Trade (TBT) Committee.
system.
1 2
This guide is under the jurisdiction of ASTM Committee E30 on Forensic For referenced ASTM standards, visit the ASTM website, www.astm.org, or
Sciences and is the direct responsibility of Subcommittee E30.12 on Digital and contact ASTM Customer Service at service@astm.org. For Annual Book of ASTM
Multimedia Evidence. Standards volume information, refer to the standard’s Document Summary page on
Current edition approved Jan. 1, 2023. Published February 2023. Originally the ASTM website.
approved in 2017. Last previous edition approved in 2017 as E3115 – 17. DOI: Available from National Institute of Standards and Technology (NIST), 100
10.1520/E3115-17R23. Bureau Dr., Stop 1070, Gaithersburg, MD 20899-1070, http://www.nist.gov.
Copyright © ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959. United States
E3115 − 17 (2023)
4.2 Image quality also plays a major role in determining the 5.1.4.1 There is sufficient and uniform lighting to capture all
extent to which a trained facial examiner is able to reach a visible skin characteristics (that is, blemishes, moles, marks,
conclusion as to whether two images containing faces are etc.).
likely to be of the same person or not. This applies to either
5.1.4.2 To avoid hot spots and shadows on the subject’s
reviewing a FR system candidate result set or 1:1 image
face.
comparisons.
5.1.4.3 The 0.3 m to 0.6 m (1 ft to 2 ft) distance (with or
without a backlight) between the background and the subject is
4.3 This guide provides guidance for the capture of facial
intended to reduce background shadows.
images under controlled, semi-controlled, and uncontrolled
5.1.5 Fig. 2 provides examples of optimal facial images
scenarios for constraints which can be categorized into the
following types of requirements: captured. Frontal, right, left, and three-quarter profile images
should be captured as these provide additional value for
4.3.1 Scene, refers to the content, subject and background in
the image, examiners undertaking forensic comparison. The subject’s
head is positioned in the image as shown.
4.3.2 Photographic, refers to lighting, focus and other
constraints required for image capture, and
5.1.6 Automated image quality software is available from
4.3.3 Digital, refers to the conversion of the captured image
various commercial suppliers that can help to determine if the
into a digital record.
frontal image is captured as per the recommendations.
However, in all cases, a manual check is advised as the
5. Scenarios
software may not take into account all of the constraints.
5.1 Controlled Acquisition:
5.2 Semi-Controlled Acquisition:
5.1.1 This scenario is when all constraints can be controlled
5.2.1 This scenario refers to when some, but not all,
including equipment, the photographic environment (camera
constraints can be controlled. Examples of this include pass-
position, lighting, distance, background, and resolution), and
port photos not taken in a controlled environment, law enforce-
the pose and positioning of the subject. The subject can be
ment mobile capture, crime scenes, access control, walk-
directed or positioned, the environment can be arranged to
through automated gates.
provide ideal illumination, and suitable equipment is available.
5.2.2 In a semi-controlled environment, the following con-
5.1.2 Referenced document ANSI/NIST-ITL-1-2011, Up-
straints should be considered as a priority:
date 2015, Annex E, provides specifications on all aspects of
5.2.2.1 Illumination,
controlled acquisition scenarios.
5.2.2.2 A single full frontal face with open eyes and neutral
5.1.3 Annex A1 in this guide presents illustrative examples
expression.
for controlled capture scenarios.
5.2.2.3 Elimination of convex lens distortion (subject
5.1.4 Fig. 1 provides an example of an optimal setting for a
should be more than 1 m (3 ft) from the camera),
controlled capture environment. The selection and placement
of the lighting addresses the following variables: 5.2.2.4 Elimination of occlusions, and
FIG. 1 Example of a Controlled Acquisition Environment
E3115 − 17 (2023)
FIG. 2 Example Poses from a Controlled Acquisition Environment
5.2.2.5 Where available, multiple images should be cap- 5.3.2.2 Position the camera to get the best pose possible or
tured to compensate for shortcomings in individual images.
provide a visual attractor to influence the pose,
5.3.2.3 A single full frontal face with open eyes,
5.3 Uncontrolled Acquisition:
5.3.1 This scenario refers to when neither the environment
5.3.2.4 Elimination of convex lens distortion (subject
nor the subject can be controlled (for example, surveillance,
should be more than 1 m (3 ft) from the camera), and
hand held camera, body cameras, cell phones, etc.). It is
5.3.2.5 In these uncontrolled scenarios, multiple images
characterized by high variations in quality and content and
should be captured to compensate for shortcomings in indi-
typically requires human review and specialized tools to
vidual images.
identify and extract usable facial content. (See NIST Special
Publication 500-280v2.)
6. Keywords
5.3.2 In these situations, the person capturing the image
6.1 capture equipment; facial image; facial recognition
should improvise to get the best image possible (see Fig. 3):
5.3.2.1 When appropriate, use a camera flash or additional
lights source(s) to improve illumination,
E3115 − 17 (2023)
NOTE 1—Tennessee Bureau of Investigation, “Mug Shot Best Practices Guide,” available from https://www.tn.gov/content/dam/tn/tbi/documents/Mug
Shot Best Practices Poster.pdf.
FIG. 3 Examples of Improper Poses from a Controlled Acquisition Environment
E3115 − 17 (2023)
ANNEX
(Mandatory Information)
A1. TABLES
A1.1 See Tables A1.1-A1.3.
TABLE A1.1 Description of a Controlled Acquisition Environment
No. Item Description Comments
1 Illumination Lighting shall uniformly illuminate the subject and the Use of an optional third light as a backlight (to eliminate shadows
background. on the background) generally requires about 1 m (3 ft) of
additional floor space behind the subject. This additional space
may not be available in all environments.
Hot spots or reflections shall be minimized. Use of flash is discouraged.
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.