Competition for Most Effective Identity Verification Systems
In a significant development, psychologists from the University of New South Wales Sydney (UNSW Sydney) have collaborated with the Australian Passport Office (DFAT) to create the Glasgow Face Matching Test 2 (GFMT2). This new test, published in the journal Behavior Research Methods with the DOI 10.3758/s13428-021-01638-x, aims to improve the accuracy of facial recognition software and prevent false identity matches.
The GFMT2 test targets high-performing facial recognition individuals, known as super-recognisers, who can review identity matches made by facial recognition software. By identifying these individuals, the test can help prevent wrongful arrests, a criticism often levied against face recognition software.
The development of the GFMT2 test is part of a decade-long collaboration with professional groups, including the Australian Passport Office, and was also supported by researchers at the University of Glasgow. Professor Mike Burton from the School of Psychology at the University of York and Dr Rob Jenkins from the School of Psychology at the University of York were instrumental in its development.
The test involves matching faces across changes that make face identification difficult in real-world tasks. It also includes tests that target low-performing face recognition individuals, such as those with prosopagnosia, or 'face blindness'. All tests are available free for scientific use, promoting transparency and academic progress.
The new GFMT2 test is a response to the requirements of professional groups, including visa processors, passport issuers, border control officers, police, contract tracers, and security staff in private industry. The test will be able to be used in a number of countries, including Australia, New Zealand, the UK, and Canada.
Recent work suggests that current professional training courses in face identification do not improve people's performance. The GFMT2 test allows for before and after comparisons to assess the impact of training and other interventions.
The Australian federal government has been considering the introduction of a centralised database that would host photos collected by a range of state and federal agencies. The GFMT2 test, with its potential to improve facial recognition accuracy, could play a crucial role in such a system.
In summary, the GFMT2 test is a significant step forward in improving the accuracy of facial recognition software. By identifying super-recognisers and targeting low-performing individuals, the test promises to prevent false identity matches and wrongful arrests. The test's wide availability for scientific use will facilitate widespread research, validation, and improvement in face recognition studies.
Read also:
- Understanding Hemorrhagic Gastroenteritis: Key Facts
- Stopping Osteoporosis Treatment: Timeline Considerations
- Tobacco industry's suggested changes on a legislative modification are disregarded by health journalists
- Expanded Community Health Involvement by CK Birla Hospitals, Jaipur, Maintained Through Consistent Outreach Programs Across Rajasthan
