Hostname: page-component-586b7cd67f-vdxz6 Total loading time: 0 Render date: 2024-11-22T14:14:38.911Z Has data issue: false hasContentIssue false
  • English
  • Français

Use of Facial Recognition Software to Identify Disaster Victims With Facial Injuries

Published online by Cambridge University Press:  10 April 2017

John Broach ,
Rothsovann Yong ,
Mary-Elise Manuell  and
Constance Nichols
John Broach*
Affiliation:
University of Massachusetts Medical School/University of Massachusetts Memorial Medical Center, Worcester, Massachusetts
Rothsovann Yong
Affiliation:
Department of Emergency Medicine, Lowell General Hospital, Lowell, Massachusetts
Mary-Elise Manuell
Affiliation:
Urgent Care, Harrington HealthCare System, Southbridge, Massachusetts
Constance Nichols
Affiliation:
University of Massachusetts Medical School/University of Massachusetts Memorial Medical Center, Worcester, Massachusetts
*
Correspondence and reprint requests to John Broach, MD, MPH, MBA, FACEP, UMass Medical School/UMass Memorial Medical Center, 55 Lake Avenue North, Worcester, MA 01655 (e-mail: [email protected]).
Get access Rights & Permissions [Opens in a new window]

Abstract

Objective

After large-scale disasters, victim identification frequently presents a challenge and a priority for responders attempting to reunite families and ensure proper identification of deceased persons. The purpose of this investigation was to determine whether currently commercially available facial recognition software can successfully identify disaster victims with facial injuries.

Methods

Photos of 106 people were taken before and after application of moulage designed to simulate traumatic facial injuries. These photos as well as photos from volunteers’ personal photo collections were analyzed by using facial recognition software to determine whether this technology could accurately identify a person with facial injuries.

Results

The study results suggest that a responder could expect to get a correct match between submitted photos and photos of injured patients between 39% and 45% of the time and a much higher percentage of correct returns if submitted photos were of optimal quality with percentages correct exceeding 90% in most situations.

Conclusions

The present results suggest that the use of this software would provide significant benefit to responders. Although a correct result was returned only 40% of the time, this would still likely represent a benefit for a responder trying to identify hundreds or thousands of victims. (Disaster Med Public Health Preparedness. 2017;11:568–572)

Keywords

disaster medicinedisaster victim identificationfacial recognitionmass casualty incidents
Type
Original Research
Information
Disaster Medicine and Public Health Preparedness , Volume 11 , Issue 5 , October 2017 , pp. 568 - 572
Copyright
Copyright © Society for Disaster Medicine and Public Health, Inc. 2017 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1. Federal Emergency Management Agency (FEMA). Post-Disaster Reunification of Children: A Nationwide Approach. https://www.fema.gov/media-library/assets/documents/85559. Published November 2013. Accessed March 22, 2017.Google Scholar
2. Morgan, OW, Sribanditmongkol, P, Perera, C, et al. Mass fatality management following the South Asian tsunami disaster: case studies in Thailand, Indonesia, and Sri Lanka. PLoS Med. 2006;3(6):e195. https://doi.org/10.1371/journal.pmed.0030195.CrossRefGoogle ScholarPubMed
3. Tsokos, M, Lessig, R, Grundmann, C, et al. Experiences in tsunami victim identification. Experiences in tsunami victim identification. Int J Leg Med. 2006;120(3):185-187. doi: 10.1007/s00414-005-0031-4 CrossRefGoogle ScholarPubMed
4. Nager, A. Family reunification: concepts and challenges. Clin Pediatr Emerg Med. 2009;10(3):195-207.CrossRefGoogle Scholar
5. Byard, R, Winskog, C. Potential problems arising during international disaster victim identification (DVI) exercises. Forensic Sci Med Pathol. 2010;6(1):1-2. https://doi.org/10.1007/s12024-009-9141-5.CrossRefGoogle ScholarPubMed
6. InterPol. Disaster Victim Identification (DVI). http://www.interpol.int/INTERPOL-expertise/Forensics/DVI. Accessed March 22, 2017.Google Scholar
7. Wright, K, Mundorff, A, Chaseling, J, et al. A new disaster victim identification management strategy targeting “near identification-threshold” cases: experiences from the Boxing Day tsunami. Forensic Sci Int. 2015;250(May):91-97. https://doi.org/10.1016/j.forsciint.2015.03.007.CrossRefGoogle ScholarPubMed
8. Broughton, D, Allen, E, Hannemann, R, et al. Reuniting fractured families after a disaster: the role of the National Center for Missing & Exploited Children. Pediatrics. 2006;117(5). https://doi.org/10.1542/peds.2006-0099S.Google ScholarPubMed
9. Bikker, J. Disaster victim identification in the information age: the use of personal data, post-mortem privacy and the rights of the victim’s relatives. Scripted. 2013;10:1. https://script-ed.org/article/asas/.Google Scholar
10. Levy, G, Blumberg, N, Kreiss, Y, et al. Application of information technology within a field hospital deployment following the January 2010 Haiti earthquake disaster. J Am Med Inform Assoc. 2010;17:626e630.CrossRefGoogle ScholarPubMed
11. McHugh, M. Facebook can recognize you don’t show your face. Wired Magazine. http://www.wired.com/2015/06/facebook-can-recognize-even-dont-show-face/. Published June 24, 2015. Accessed March 22, 2017.Google Scholar