Australia DoD looks to facial recognition to ID bodies in disaster response
The Australian Department of Defence is working on a project using artificial intelligence (AI) and facial recognition to identify the dead.
The claim comes from Richard Bassed, head of Melbourne-based Monash University’s Department of Forensic Medicine (VIFM).
According to Bassed, the project may be up and running within five years.
“Very early stages,” he says in a blog post on the University’s website. “But we are thinking that we might be able to identify quite large numbers of people, and thus reduce the cost and time required to identify the remainder.”
The professor mentions the Türkiye-Syria earthquakes and how both countries are struggling with the growing death toll.
“Both Türkiye and Syria are member countries of Interpol, which designed and implemented the standard operating procedure for disaster victim identification,” Bassed explains.
“But current news reports say bodies are being buried in mass graves on site in Türkiye-Syria, many without being formally identified, with a shortage of forensic investigators on the ground.”
Similar issues are also arising following mass deaths ensuing from conflicts, which also brings about politics-related problems.
“The war graves in Iraq and Iran and Syria and everywhere else? People aren’t trying to do anything there, partly because of the political problems in some of those countries, but also because of the huge, huge cost and effort to do it,” Bassed writes.
Facial recognition is being used to reunite children with surviving family in Türkiye, however.
The collaborative VIFM-Department of Defence project would aim to solve these issues by creating an extensive database of face images (from passports, driver’s licenses and other IDs) alongside a facial recognition algorithm to identify them.
“We’re going to need to either tweak a current algorithm or create our own facial recognition algorithm that will work reliably with photographs of them when the body is found,” Bassed says.
“Then you can start comparing the photos while alive with the post-mortem images of the deceased through a machine-learning facial recognition algorithm.”
A separate VIFM project is looking at getting full-body CT scans of Victorian bodies going to the institute.
The scan shows the bones but also how a face sits on them. The project aims to create an algorithm capable of rebuilding a face on an unknown skull (enhanced with DNA matching to build hair color, eye color, and other facial features).
Human identification market to reach $3B by 2033
The VIFM research projects come amidst a sharp increase in the adoption of human identification technologies.
According to new figures by Future Market Insights Global and Consulting Pvt, the global human identification market is set to be valued at $1.2 billion in 2023.
A recent report by the companies also suggests this market is forecast to rise to $3 billion by 2033, growing at a compound annual growth rate (CAGR) of 9.6 percent through the next decade.
The research document suggests the U.S. will account for a large portion of the global human ID market in the projected period, but Asia Pacific (particularly Japan and South Korea) is predicted to hold the main share.
Human identification techniques via DNA are also being increasingly used in missing person investigations in India to identify women and children who are sexually abused.
Further, the report shows that more and more forensic laboratories worldwide are witnessing the rising availability of government financing, representing the most innovative area for critical players to invest.
The figures come months after Pakistan confirmed the development of biometric systems to identify dead bodies by fingerprints.