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

Broach, John; Yong, Rothsovann; Manuell, Mary-Elise; Nichols, Constance

doi:10.1017/dmp.2016.207

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…16 While some of this information may be extremely useful, such as photographs for use with facial recognition software, special framing for these requests may be helpful to encourage guardians to share this particular data. 17,18 Findings from this study indicate that a reunification system needs to clearly delineate with whom the child's personal information will be shared, have clear parameters for the removal of information, and outline the steps used to protect information. Half of the respondents expressed concerns about these topics.…”

Section: Discussionmentioning

confidence: 98%

Separated After a Disaster: Trust and Privacy Issues in Sharing Children’s Personal Information

Charney

Rebmann

Esposito

et al. 2019

Disaster med. public health prep.

View full text Add to dashboard Cite

Background:After disasters, unaccompanied children may present to an emergency department requiring reunification. An effective reunification system depends on the willingness of guardians to utilize it.Objective:Assess guardian willingness to share children’s personal information for reunification purposes after a disaster, perceived concerns and beliefs, and trust in reunification agencies.Methods:Guardians of children presenting to 2 pediatric emergency departments were approached to participate in a survey-based study. Willingness to share their children’s personal information was scored on a scale of 1 to 19 (1 point per item). Perceived concerns about and importance of sharing information, level of trust in reunification agencies, and guardian demographics were collected. Chi-square was used to compare trust and attitudes/beliefs. Multivariate linear regression was used to determine factors associated with willingness to share information.Results:A total of 363 surveys were completed (response rate, 80%). Most guardians (95.6%) were willing to share at least some information (mean, 16 items; range, 1-19). Half were concerned about protection (55.4%) or abuse (52.3%) of their child’s information. Hospitals were trusted more than other reunification agencies (P < .001). Perception of reunification importance was associated with willingness to share (P < .001).Conclusions:Guardians are willing to share their children’s information to facilitate reunification after disasters, but have privacy concerns.

show abstract

Section: Discussionmentioning

confidence: 98%

Separated After a Disaster: Trust and Privacy Issues in Sharing Children’s Personal Information

Charney

Rebmann

Esposito

et al. 2019

Disaster med. public health prep.

View full text Add to dashboard Cite

show abstract

“…We found scarce examples in literature of studies simulating a specific disease-state using techniques such as facial manipulation with moulage or make-up. One other study took photographs of volunteers before and after application of moulage designed to simulate traumatic facial injuries, and found that upon examination of these photographs by a facial analysis software, between 39 and 90% of photographs of injured patients were identified correctly ( 42 ). Clearly, synthetic and augmented datasets have the potential to enable researchers to “tailor” data to a specific context, but their generation and use is not without challenges.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning for Identification of Acute Illness and Facial Cues of Illness

et al. 2021

View full text Add to dashboard Cite

Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves the assessment of patients' health status, as shown in genetic syndromes and acute coronary syndrome. It is unknown if the inclusion of clinical gestalt improves ML-based classification of acutely ill patients. As in previous research in ML analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt.Objective: To assess whether a deep learning algorithm trained on a dataset of simulated and augmented facial photographs reflecting acutely ill patients can distinguish between healthy and LPS-infused, acutely ill individuals.Methods: Photographs from twenty-six volunteers whose facial features were manipulated to resemble a state of acute illness were used to extract features of illness and generate a synthetic dataset of acutely ill photographs, using a neural transfer convolutional neural network (NT-CNN) for data augmentation. Then, four distinct CNNs were trained on different parts of the facial photographs and concatenated into one final, stacked CNN which classified individuals as healthy or acutely ill. Finally, the stacked CNN was validated in an external dataset of volunteers injected with lipopolysaccharide (LPS).Results: In the external validation set, the four individual feature models distinguished acutely ill patients with sensitivities ranging from 10.5% (95% CI, 1.3–33.1% for the skin model) to 89.4% (66.9–98.7%, for the nose model). Specificity ranged from 42.1% (20.3–66.5%) for the nose model and 94.7% (73.9–99.9%) for skin. The stacked model combining all four facial features achieved an area under the receiver characteristic operating curve (AUROC) of 0.67 (0.62–0.71) and distinguished acutely ill patients with a sensitivity of 100% (82.35–100.00%) and specificity of 42.11% (20.25–66.50%).Conclusion: A deep learning algorithm trained on a synthetic, augmented dataset of facial photographs distinguished between healthy and simulated acutely ill individuals, demonstrating that synthetically generated data can be used to develop algorithms for health conditions in which large datasets are difficult to obtain. These results support the potential of facial feature analysis algorithms to support the diagnosis of acute illness.

show abstract

“…This could save time and money while sparing victims and first responders from the traumatic experience of looking through numerous victim images in search of a "match." 17 According to Frank Hersey's report on biometric update, FRT has been proven helpful for rescuing children from the rubble of the recent earthquake in the southern region of Turkey. 18 The report mentioned that around 144 children have been identified.…”

Section: Disaster Victim Identification/ Examination Of Unidentified ...mentioning

confidence: 99%

“…Due to the availability of powerful facial recognition software, it is possible that commercially accessible technologies can assist disaster responders in successfully reuniting victims with their families by minimizing the number of photos that need to be manually reviewed. This could save time and money while sparing victims and first responders from the traumatic experience of looking through numerous victim images in search of a “match.” 17 According to Frank Hersey's report on biometric update, FRT has been proven helpful for rescuing children from the rubble of the recent earthquake in the southern region of Turkey. 18 The report mentioned that around 144 children have been identified.…”

Section: Applications Of Facial Recognition Technologymentioning

confidence: 99%

Global adoption of facial recognition technology with special reference to India—Present status and future recommendations

Guleria,

Krishan,

Sharma

et al. 2024

Med Sci Law

View full text Add to dashboard Cite

The face is the most essential part of the human body, and because of its distinctive traits, it is crucial for recognizing people. Facial recognition technology (FRT) is one of the most successful and fascinating technologies of the modern times. The world is moving towards contactless FRT after the COVID-19 pandemic. Due to its contactless biometric characteristics, FRT is becoming quite popular worldwide. Businesses are replacing conventional fingerprint scanners with artificial intelligence—based FRT, opening up enormous commercial prospects. Security and surveillance, authentication/access control systems, digital healthcare, photo retrieval, etc., are some sectors where its use has become essential. In the present communication, we presented the global adoption of FRT, its rising trend in the market, utilization of the technology in various sectors, its challenges and rising concerns with special reference to India and worldwide.

show abstract

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

Cited by 6 publications

References 8 publications

Separated After a Disaster: Trust and Privacy Issues in Sharing Children’s Personal Information

Separated After a Disaster: Trust and Privacy Issues in Sharing Children’s Personal Information

Deep Learning for Identification of Acute Illness and Facial Cues of Illness

Global adoption of facial recognition technology with special reference to India—Present status and future recommendations

Contact Info

Product

Resources

About