University of Bradford team develops digital face-ageing that could help in sear
RESEARCHERS at the University of Bradford have developed a technique that could revolutionise the way police are able to search for people who have been missing for long periods.
Source: Chris Young
The team has created a new method of ageing facial images, which could enhance the search for long-term missing people, especially those who went missing when they were young children.
“Aged” images have become prominent in the media in recent years, particularly in the high-profile searches for missing children like Madeleine McCann.
The method, which was developed by the university’s Centre for Visual Computing, maps out the key features like the shape of the cheek, mouth and forehead, of a face at a certain age. This information is fed to a computer algorithm, which then synthesises new features for the face to produce photographic quality images of the face at different ages.
A key feature of the new method is that it teaches the machine how humans age by feeding the algorithm facial feature data from a large database of individuals at various ages. This method improves on existing techniques, achieving greater levels of accuracy to those currently used by police.
The findings are today being presented at the International Conference on Missing Children and Adults at Abertay University, Dundee, and have also been published in the Journal of Forensic Sciences.
Professor Hassan Ugail, of the centre, is leading the research. He said: “Each year around 300,000 missing person cases are recorded in the UK alone. This has been part of our motivation in endeavouring to improve current techniques of searching for missing people, particularly those who have been missing for some considerable time.”
As a test case, the researchers chose to work on the case of Ben Needham, who disappeared on the Greek island of Kos on July 24, 1991, when he was only 21 months old. Since then, several images have been produced by investigators showing how Ben might look at ages 11-14 years, 17-20 years, and 20-22 years. The team used its method to progress the image of Ben to the ages of 6, 14 and 22 years. The resulting images show very different results, which the researchers believe more closely resemble what Ben might look like today.
Professor Ugail added: “No criticism is implied of existing age progression work. Instead we are presenting our work as a development and improvement that could make a contribution to this important area of police work. We are currently working with the relevant parties to further test our method.”