Broach John, Yong Rothsovann, Manuell Mary-Elise, Nichols Constance
1University of Massachusetts Medical School/University of Massachusetts Memorial Medical Center,Worcester,Massachusetts.
2Department of Emergency Medicine,Lowell General Hospital,Lowell,Massachusetts.
Disaster Med Public Health Prep. 2017 Oct;11(5):568-572. doi: 10.1017/dmp.2016.207. Epub 2017 Apr 10.
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.
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.
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.
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).
在大规模灾难发生后，遇难者身份识别常常是一个挑战，也是救援人员试图让家人团聚并确保正确识别死者身份时的首要任务。本调查的目的是确定目前市面上可买到的面部识别软件能否成功识别面部受伤的灾难受害者。
对106人在涂抹旨在模拟面部创伤的油灰前后进行拍照。使用面部识别软件对这些照片以及志愿者个人照片集里的照片进行分析，以确定这项技术能否准确识别面部受伤的人。
研究结果表明，救援人员在提交的照片与受伤患者照片之间获得正确匹配的概率在39%至45%之间，如果提交的照片质量最佳，在大多数情况下正确匹配的百分比会高得多，超过90%。
目前的结果表明，使用该软件将为救援人员带来显著益处。尽管只有40%的时间能得到正确结果，但这对于试图识别成百上千名受害者的救援人员来说仍可能是有益的。（《灾难医学与公共卫生防范》。2017年；11:568 - 572）
