Can you spot a sex abuser from their hands?
Scientists hope to help catch attackers using computer algorithms
Scientists are calling for the public to help with pioneering research to train computers to identify child abusers from images of their hands.
The BBC reports that often, “the backs of hands are the only visible features of abusers in footage and images shared online”.
Now, researchers from the universities of Lancaster and Dundee hope to teach computers to spot anatomical features in anonymous images sent in by volunteers.
This “will allow algorithms to be designed that will help police to link suspects to crimes just from images of their hands”, according to ITV.
The broadcaster adds that the team behind the study need more than 5,000 “citizen scientists” to take part, in order to get enough data to confirm beyond reasonable doubt that our hands are unique.
–––––––––––––––––––––––––––––––For a round-up of the most important stories from around the world - and a concise, refreshing and balanced take on the week’s news agenda - try The Week magazine. Start your trial subscription today –––––––––––––––––––––––––––––––
Forensic anthropologist Sue Black said: “Our hands display many anatomical differences due to our development, influence of genetics, ageing, environment or even accidents.
“We know that features such as vein patterns, skin creases, freckles, moles, and scars are different between our right and left hands, and even different between identical twins.”
Black added that the project could deliver a “step-change” that allows researchers to understand what makes hands unique and produce “new forensic tools that will help law enforcement apprehend those who harm the most vulnerable in our society”.
A web-based app has been launched that allows anyone aged 18 or over to contribute their hand images to the project on smartphones.
Researchers say the images will not be shared with any external agencies and will be destroyed at the end of the five-year research project, which is being funded through a €2.5m (£2.1m) grant from the European Research Council.
Bryan Williams, lecturer in biometrics and human identification at Lancaster University, said: “The tools we will develop will reliably and robustly inform decisions in criminal courts. They could also be used to assist law enforcement agencies to rapidly and autonomously analyse hours of footage and thousands of offensive images.”
If you would like to contribute to the project, the app is available at h-unique.lancaster.ac.uk