ASTM E3115-17(2023) PDF
Standard Guide for Capturing Facial Images for Use with Facial Recognition Systems
Standard Guide for Capturing Facial Images for Use with Facial Recognition Systems
- Статус документа:
- Действующий
- Формат:
- Электронный (PDF)
- Количество страниц:
- 7
- Дата публикации:
- 1 января 2023 г.
- Издание:
- E3115
- ICS:
- 35.240.15
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.
Abstract
Overview
ASTM E3115-17(2023): Standard Guide for Capturing Facial Images for Use with Facial Recognition Systems provides comprehensive guidance for practitioners involved in capturing facial images intended for automated facial recognition (FR) systems or manual examination by facial experts. Developed by ASTM, this international standard outlines procedures and best practices to achieve high-quality facial image capture under controlled, semi-controlled, and uncontrolled conditions. The goal is to optimize image quality, which directly impacts the accuracy and reliability of facial recognition in applications such as passports, law enforcement, and secure access control.
Key Topics
-
Image Quality Criteria High-quality images are essential for both automated facial recognition accuracy and effective manual comparison by trained examiners. The guide identifies three main categories affecting capture:
- Scene: Involves subject position and background, avoiding distractions and ensuring a neutral backdrop.
- Photographic: Focuses on lighting, camera focus, and lens distortion to minimize shadows, glare, and other artifacts.
- Digital: Covers the digital recording and storage of facial images, ensuring proper file format, compression, and metadata capture.
-
Acquisition Scenarios The standard differentiates among:
- Controlled Acquisition: All factors are managed, producing the highest quality images (e.g., passport offices, police stations).
- Semi-Controlled Acquisition: Some constraints may be relaxed (e.g., mobile law enforcement, on-site passport photos).
- Uncontrolled Acquisition: Minimal control over the environment or subject, common in surveillance and field operations, requiring adaptability and often post-capture human review.
-
Equipment Recommendations
- Use high-quality digital cameras with manual override capabilities.
- Avoid webcams, cell phone cameras, or devices lacking manual exposure settings unless necessary.
- Employ tripods for stability and ensure portrait orientation.
-
Subject Presentation
- Subjects should have a neutral expression, closed mouths, and direct gaze.
- Remove accessories and headwear except for medical or religious reasons.
- Hair should be moved away from the face and ears visible.
- Only one face per image; ensure the subject’s face is unobstructed.
Applications
The guidance and requirements in ASTM E3115-17(2023) are widely applicable in a variety of sectors that rely on facial recognition technology and high-integrity image capture:
- Passport and Visa Issuance: Ensuring standardized, compliant photos to improve international interoperability and system accuracy.
- Law Enforcement: Creating reliable mugshots and supporting forensic facial comparison.
- Access Control Systems: Improving facial authentication at secure facilities and automated gates.
- Mobile and Field Capture: Assisting officers and security personnel in attaining best possible quality under less-than-ideal conditions.
- Forensic Analysis: Supporting evidence integrity and accuracy in criminal investigations.
Following this standard helps organizations meet regulatory, security, and operational requirements for facial image quality.
Related Standards
-
ANSI/NIST-ITL-1-2011, Update 2015 Defines environmental and subject specifications for biometric data, referenced for technical criteria in controlled capture.
-
NIST Special Publication 500-280v2 Provides mobile identification best practice recommendations.
-
ASTM E2916 Focuses on digital and multimedia evidence terminology, relevant when documenting and interpreting captured images.
Implementing ASTM E3115-17(2023) alongside these related standards supports consistency, interoperability, and best practices in the capture and use of facial images for recognition systems worldwide.
Технические детали
- Технический комитет
- E30 - Forensic Sciences
- SKU
- ASTM E3115-17(2023)
Похожие стандарты
Другие стандарты ASTM
ASTM-TPT-47
Phase I & Phase II Environmental Site Assessment Processes
Phase I & Phase II Environmental Site Assessment Processes
ASTM-TPT-8
Phase I Environmental Site Assessment Practices For Commercial Real Estate: Phase I Site Assessment & Transac…
ASTM-TPT-1137
ASTM D975 Standard Specification for Diesel Fuel
ASTM D975 Standard Specification for Diesel Fuel
ASTM-TPT-1202
ASTM D8421 Standard Test Method for Determination of Per- and Polyfluoroalkyl Substances (PFAS) in Aqueous Ma…
ASTM D8421 Standard Test Method -- eLearning Course
ASTM-TPT-691
Microaprendizagem para D4057: Amostragem de ponto (PT)
D4057 Microlearning: Spot Sampling Portuguese
ASTM-TPT-1091
Metodo de prueba estandar D4052 de ASTM -- Curso de aprendizaje electrónico (ES)
Modulo eLearning para ASTM D4052 en espanol
ASTM ACEM20180086
Using Neutron Radiography to Quantify the Settlement of Fresh Concrete
Specifications have been implemented for concrete bridge decks in North America that restrict the use of higher slump concrete mixtures primarily because of concerns about differential settlement and…
ASTM ACEM20180041
Experimental Study of Competing Failure of Reinforced Concrete Based on the Weibull Distribution
To predict the failure lifetime of reinforced concrete, a current accelerating corrosion test was performed on concrete by simulating the environment in an area with saline soil. To study the concret…