Live
- Raj Thackeray releases MNS election Manifesto with a ‘key’ to implementing it
- Gold prices likely to further come down with no near-term positive triggers
- Tough decision, but it's the right one: Southee on Test retirement
- After caste census, Dalits, tribals, poor will recognise their true strength: Rahul Gandhi
- Who was Birsa Munda, whose 'Ulgulan' declared the end of British rule in Jharkhand?
- Logistic firm Delhivery’s profit tanks over 80 pc in April-Sep period
- Five selected as Indian Rhodes Scholars for 2025
- Raj Thackeray releases MNS election Manifesto with a ‘key’ to implementing it
- COP29: 3 methodologies approved for issuing high-integrity carbon credits
- MP: Celebrations of Birsa Munda's birth anniversary begin in presence of Guv, CM in Shahdol
Even smartphones can fail to detect morph photos
A group of researchers has demonstrated that both humans and smartphones show a degree of error in distinguishing face morph photos from their \'real\' faces on fraudulent identity cards.
A group of researchers has demonstrated that both humans and smartphones show a degree of error in distinguishing face morph photos from their 'real' faces on fraudulent identity cards. Researchers at the University of York in Britain investigated what the success rate would be like if two faces were morphed together to create a "new" face.
"We use photo ID all the time, not just at borders, and we know that people are not very accurate when matching the photo to the real face," said Professor Mike Burton from University of York's Department of Psychology.
"In recent years, we have seen more examples of photo IDs that have been created by morphing two faces together, which can be used as fraudulent ID by both parties. Our research is important in highlighting the potential security problem with this and quantifying the risk of this type of fraud being missed," Burton added.
In their study, published in the journal PLOS ONE, the researchers found that initially human viewers were 68 per cent of the time unable to distinguish a 50/50 morph photo from its contributing photos.
However, after simply briefing the viewers to look out for manipulated, "fraudulent" images, the error rate dropped greatly to 21 per cent. The team also looked at smartphone software, which achieved similar results to briefed human viewers, with an error rate of 27 per cent.
These rates, however, are still significantly higher than error rates when comparing two photos of entirely different people. "Raising awareness of this type of fraud and including it in training schemes for frontline staff can help overcome these issues and with new technologies coming on line, it should be a challenge that can be tackled with some success," Burton added.
