EPSRC logo

Details of Grant 

EPSRC Reference: GR/S98504/01
Title: SWISS - Significant Witness Identification of Suspects System
Principal Investigator: Solomon, Dr CJ
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Kent County Constabulary VisionMetric Ltd
Department: Sch of Physical Sciences
Organisation: University of Kent
Scheme: Standard Research (Pre-FEC)
Starts: 01 October 2004 Ends: 30 September 2006 Value (£): 106,161
EPSRC Research Topic Classifications:
Cognitive Science Appl. in ICT Image & Vision Computing
Software Engineering
EPSRC Industrial Sector Classifications:
Information Technologies
Related Grants:
GR/S98511/01
Panel History:  
Summary on Grant Application Form
A 24 month programme of research and development is proposed whose aim is to produce a fast, easy-to-use and high quality facial composite system to be deployed and rapidly operated at the scene-of-crime (or immediate aftermath) by eye-witnesses and/or police officers using standard laptop computers and hand-held devices. Such a system will provide significant new tactical advantage to Police Forces allowing high-quality composites to be secured in a way which guarantees the integrity of eyewitness testimony, greatly enhances its subsequent evidential value and which provides capacity for immediate search on a database of persistent offenders. Success in this project will thus not only effect major improvements in accuracy and cost over existing commercial systems but will also considerably extend the operational utility and application domain of facial composites.The research programme will involve close collaboration between the University of Kent (mathematical and computational research), Goldsmiths College, London (psychological evaluation and testing), The Kent County Constabulary (operational system design, legal advice and field trials) and VisionMetric Ltd (software development, graphical user interface and system integration). The research programme consists of 5 inter-related activities i) Interactive, evolutionary algorithms for generation of near photo-quality composites using a statistical appearance model of human facial appearance (Kent). ii) Encoding and matching algorithms for interrogation of police databases (Kent). iii) Implementation of these algorithms on standard police hardware for functional operation (VisionMetric Ltd and Kent) iv) A series of psychological evaluations and tests on both the core methodology and the human-machine interface (Goldsmiths). v) Field trials and assessment of system's operational utility (Kent Police).
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL: http://www.visionmetric.com
Further Information:  
Organisation Website: http://www.kent.ac.uk