Researchers from Bradford University have designed a new face-aging technique that may aid in the search for missing people.
Focusing on the details of a person’s face, such as the shape of their cheek, mouth and forehead at a certain age, images are put into a computer algorithm where new features for the face are produced. The images are created based on a method that teaches the machine about aging by exposing it to a database of human facial features at various ages.
Professor Hassan Ugail, of Bradford's Centre for Visual Computing, 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."
Applying a method of predictive modeling to age progression, researchers, using the facial data from the database, tested the method by running the algorithm for individual’s pictures backwards, thereby de-aging them. The image that results from the de-aging process is then compared with images of the individual at a younger age.
Using the case of Ben Needham (who has never been found after disappearing from the Greek island of Kos on July 24, 1991, when he was only 21 months old), researchers compared the images created by investigators showing what Ben might look like at 11-14 years, 17-20 years and 20-22 years to those created by the research team using the algorithm. The images created using the algorithm are significantly different than the images created during previous investigations.
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. We are also developing further research plans in order to develop this method so it can be incorporated as a biometric feature, in face recognition systems, for example."
"Our method generates more individualised results and hence is more accurate for a given face. This is because we have used large datasets of faces from different ethnicities as well as gender in order to train our algorithm. Furthermore, our model can take data from an individual's relatives, if available, such as parents, grandparents and siblings. This enables us to generate more accurate and individualised ageing results. Current methods that exist use linear or one-dimensional methods whereas ours is non-linear, which means it is better suited for the individual in question."
The findings will be presented at the International Conference on Missing Children and Adults at Abertay University, Dundee in June, and have been published in the Journal of Forensic Sciences.