Home Reports Information Technology Content

The use of an ‘average face’ drastically improves facial recognition

next article

12.09.2007

Recent research shows that humans are surprisingly poor at matching a face in a photograph to that seen in real life. The situation is the same with automatic face recognition systems. In today’s surveillance society, correct photo identification is of the utmost importance and with the government’s proposed identity card scheme expected to begin in 200, the ID issue is highly controversial.

Researchers from the University of Glasgow, led by Dr Rob Jenkins and Professor Mike Burton, have developed a new technology that drastically improves the success of both human and automated systems at matching a face to a photo. Dr Jenkins spoke about this work at the BA Festival of Science on Tuesday at The BA Joseph Lister Award Lecture.

The team worked on the principle that the more familiar a person is with the face in question, the easier it is for them to recognise the face in a photograph. They collected different images of each person’s face and averaged them to make one image. Only 10 – 11 photos were required to stabilise the image, with any extra images after that making little difference. The average face image was also surprisingly resilient to errors, even with the ‘contamination’ of a third of the faces being of other people, the average face hardly changed.

Dr Jenkins said: ‘The resulting images are quite uncanny, seeming to bring out the true essence of each face.’

The averaged faces were then checked against the individual faces from which they were made. Both humans and machines were significantly better at recognising the average picture. Jenkins explained: ‘This is because the averaging process washes out aspects of the image that are unhelpful, such as lighting effects, while consolidating aspects of the image that are diagnostic of identity, such as the physical structure of the face.’

With the proposed identity card scheme looming, the breakthrough of better-than-photo recognition accuracy raises the question of whether face databases and ID documents should contain identity averages, rather than standard photographs.

‘This boost in face recognition accuracy has major implications for crime prevention and national security policies. It also demonstrates that with face recognition, as with so many other problems, we can improve machine performance by mimicking nature's solution,' said Dr Jenkins.

Dr Rob Jenkins gave his talk, ‘Identity and mistaken identity: face recognition in a surveillance society’ on 11 September at Physics PX/001, University of York as part of the BA Festival of Science.

The opportunity to present a popular and prestigious BA award lecture at the Festival of Science is offered to five outstanding communicators each year. The award lectures aim to promote open and informed discussion on issues involving science and actively encourage young scientists to explore the social aspects of their research, providing them with reward and recognition for doing so.

The BA Festival of Science will be in York from 9-15 September, bringing over 350 of the UK’s top scientists and engineers to discuss the latest developments in science with the public. In addition to talks and debates at the University of York, there will be a host of events throughout the city.

For further information about the BA Festival of Science, including an online programme, visit www.the-ba.net/festivalofscience.

This year’s BA Festival of Science is organised by the BA (British Association for the Advancement of Science) in partnership with the University of York, Science City York and the City of York Council. It is supported by the Department for Innovation, Universities and Skills, BP and Yorkshire Forward.

Lisa Hendry | Source: alphagalileo
Further information: www.the-ba.net

next article