21-i-002
Disclaimer and Conditions Regarding Use of SWGDE Documents:
SWGDE documents are developed by a consensus process that involves the best efforts of relevant subject matter experts, organizations, and input from other stakeholders to publish suggested best practices, practical guidance, technical positions, and educational information in the discipline of digital and multimedia forensics and related fields. No warranty or other representation as to SWGDE work product is made or intended.
As a condition to the use of this document (and the information contained herein) in any judicial, administrative, legislative, or other adjudicatory proceeding in the United States or elsewhere, the SWGDE requests notification by e-mail before or contemporaneous to the introduction of this document, or any portion thereof, as a marked exhibit offered for or moved into evidence in such proceeding. The notification should include: 1) The formal name of the proceeding, including docket number or similar identifier; 2) the name and location of the body conducting the hearing or proceeding; and 3) the name, mailing address (if available) and contact information of the party offering or moving the document into evidence. Subsequent to the use of this document in the proceeding please notify SWGDE as to the outcome of the matter. Notifications should be sent to secretary@swgde.org.
From time to time, SWGDE documents may be revised, updated, or sunsetted. Readers are advised to verify on the SWGDE website (www.swgde.org) they are utilizing the current version of this document. Prior versions of SWGDE documents are archived and available on the SWGDE website.
Redistribution Policy:
SWGDE grants permission for redistribution and use of all publicly posted documents created by SWGDE, provided that the following conditions are met:
- Redistribution of documents or parts of documents must retain this SWGDE cover page containing the Disclaimer and Conditions of Use.
- Neither the name of SWGDE nor the names of contributors may be used to endorse or promote products derived from its documents.
- Any reference or quote from a SWGDE document must include the version number (or creation date) of the document and also indicate if the document is in a draft status.
Requests for Modification:
SWGDE encourages stakeholder participation in the preparation of documents. Suggestions for modifications are welcome and must be forwarded to the Secretary in writing at secretary@swgde.org. The following information is required as a part of any suggested modification:
- Submitter’s name
- Affiliation (agency/organization)
- Address
- Telephone number and email address
- SWGDE Document title and version number
- Change from (note document section number)
- Change to (provide suggested text where appropriate; comments not including suggested text will not be considered)
- Basis for suggested modification
Intellectual Property:
Unauthorized use of the SWGDE logo or documents without written permission from SWGDE is a violation of our intellectual property rights.
Individuals may not misstate and/or over represent duties and responsibilities of SWGDE work. This includes claiming oneself as a contributing member without actively participating in SWGDE meetings; claiming oneself as an officer of SWGDE without serving as such; claiming sole authorship of a document; use the SWGDE logo on any material and/or curriculum vitae.
Any mention of specific products within SWGDE documents is for informational purposes only; it does not imply a recommendation or endorsement by SWGDE.
1. Purpose and Scope
The purpose of this document is to provide information on the differences between facial recognition and facial comparison to imaging examiners and their agencies, as well as the SWGDE position on the use of the results. This document is not meant to be a step-by-step guide to either automated facial recognition procedures or facial comparison. For further information on these subjects; please refer to the Facial Identification Scientific Working Group (FISWG) documents at www.FISWG.org or additional SWGDE referenced documents. [1][2][3]
2. Introduction
Both automated facial recognition and facial comparison have prolific uses. These can include both non-law enforcement (e.g., asset protection, access control and marketing) and law enforcement activity. Within the field of law enforcement, automated facial recognition is used extensively within investigations to narrow the field of persons of interest to a small candidate list, while facial comparison is completed by a trained human to review the images for similarities and dissimilarities.
3. Definitions
- Automated Facial Recognition System (FRS)
- Automated FRS algorithms compare patterns within the field of computer vision. Such approaches may not rely upon intrinsic models of what a face is, how it should appear, or what it may represent. In other words, the matching is not based on biological or anatomical models of what a face (or the features that make up a face) look like. Instead, the algorithm performance is entirely dependent upon the patterns which the algorithm developer finds to be the most useful for finding similarities. The patterns used in FRS algorithms do not correlate to obvious anatomical features, such as the eyes, nose, or mouth in a one-to-one manner, although they are affected by these features.
- Facial Comparison
- The manual examination of the differences and similarities between two facial images or a live subject and a facial image (one-to-one) for the purpose of attributing features to the same or different persons.
4. SWGDE Position on Interpretation of Results
Despite their widespread use, facial recognition and facial comparison are often misunderstood as to the relative strength of conclusions offered in each use case.
In 2017, the Bureau of Justice Assistance released a document entitled “Face Recognition Policy Development Template for Use in Criminal Intelligence and Investigative Activities” [4], which extensively describes the methods used for facial recognition, as well as highlighting the use of facial comparison.
Of particular importance, the reference document specifies that facial recognition candidate returns are not considered a positive identification. Instead, facial recognition searches are completed to narrow a list of candidates to a small sub-set, for further investigatory activity, through trained human adjudication.
Like facial recognition, facial comparison does not provide positive identifications. Rather, facial comparison examinations are meant to describe the correspondence of facial features between images, or between a human subject and imagery, providing an interpretation of the similarities and differences. As in any photographic comparison, examiners provide a clear indication as to the strength of comparison results, incorporating a descriptive statement with a standardized scale. Such scales include the observations or features that correspond to the results obtained.
In each use case, whether facial recognition or facial comparison, results must be reviewed by trained personnel following specific guidelines, recommendations, standard operating procedures and all applicable agency-specific policies. One such policy must be regarding the use of either candidate returns or comparison results as investigative leads only. Contributors should not rely solely on forensic science service provider responses as the only basis for law enforcement action. Other investigatory activity must be completed and taken into consideration prior to arrest.
5. References
[1] 2017-07-18 SWGDE Best Practices for Photographic Comparison for All Disciplines_v1-1
[2] 2019-07-16 SWGDE Technical Overview for Forensic Image Comparison
[3] 2016-06-23 SWGDE Digital and Multimedia Evidence Glossary v3
[4] “Face Recognition Policy Development Template for Use in Criminal Intelligence and Investigative Activities.” Bureau of Justice Assistance, bja.ojp.gov/library/publications/facerecognition-policy-development-template-use-criminal-intelligence-and. Accessed 14 June 2021.
[5] Phillips, P. , White, D. , O’Toole, A. , Hahn, C. and Hill, M. (2015), Perceptual expertise in forensic facial image comparison, Proceedings of the Royal Society B-Biological Sciences, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=917560. Accessed 8 June, 2022.
[6] Hahn, C. , Tang, L. , Yates, A. and Phillips, P. (2021), Forensic facial examiners vs. superrecognizers: Evaluating behavior beyond accuracy, [online] https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=932786. Accessed 8 June, 2022.
[7] Phillips, P. Jonathon, et al. “Face Recognition Accuracy of Forensic Examiners, Superrecognizers, and Face Recognition Algorithms.” Proceedings of the National Academy of Sciences, vol. 115, no. 24, 29 May 2018, pp. 6171–6176, www.pnas.org/content/115/24/6171/tab-article-info?fbclid=IwAR1zCecGIUqUI_XAVcoU983-IFONjOpH0mm50oZLam7iI8Fgqd56SFhoziY, 10.1073/pnas.1721355115.
[8] FISWG Glossary v.2.0 https://fiswg.org/fiswg_glossary_v2.0_20191025.pdf
6. History
| Revision | Issue Date | Section | History |
|---|---|---|---|
|
1.0 DRAFT |
2021-06-14 |
Imaging |
Draft for Public Comment |
|
1.1
DRAFT |
2021-09-15 |
Imaging |
Draft for Public Comment |
|
1.2
DRAFT |
2022-01-11 |
Imaging |
Draft for Public Comment |
|
1.2 |
2022-06-09 |
Imaging |
Editorial changes made prior to final
publication as Approved version 1.2 |
Version: 1.2 (June 9, 2022)