Facial composites (often known as Photo-fits or E-FITs) are used to assist Police Forces in criminal investigations. The system being developed at Kent, known as EigenFIT, combines a generative, statistical model of human facial appearance with an interactive, evolutionary search algorithm which a witness must operate to achieve the desired facial likeness.

This project will establish interactive algorithms for the generation of photo-quality facial composites for criminal investigations. Robust, accurate and fast evolutionary search strategies will be developed that incorporate fuzziness in the fitness evaluation in response to cognitively simple user decisions. The aim is to replace current systems that rely on recall and verbal description with a system that makes direct use of the highly developed human capacity for facial recognition.

Project staff and support

Mark Hoskins (Postgraduate Associate, University of Kent)
Chris Solomon (Academic supervisor, University of Kent)
Christopher Morgan (Industrial supervisor, VisionMetric)
Melvin Brown (Technology Translator, Industrial Mathematics KTN)

This project is being carried out at the University of Kent, in conjunction with VisionMetric. It is supported by an EPSRC industrial CASE award, made available through the Knowledge Transfer Network for Industrial Mathematics. Start date: October 2006; duration: 3.5 years.