| EPSRC Reference: |
GR/S06738/01 |
| Title: |
Synthesis of facial composites for improved suspect identification |
| Principal Investigator: |
Solomon, Dr CJ |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Physical Sciences |
| Organisation: |
University of Kent |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 April 2003 |
Ends: |
31 March 2005 |
Value (£): |
107,414
|
| EPSRC Research Topic Classifications: |
| Cognitive Science Appl. in ICT |
Image & Vision Computing |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Current facial composite systems used by Police Forces are time-consuming and costly and the resulting composites very variable in quality. The aim of this collaborative research programme is to explore a new method for synthesis of facial composites enabling quicker, more accurate composites to be obtained. The basic approach taken to synthesis will be through the combination of a principal components-based, facial appearance model with an interactive genetic algorithm. In the first phase of the project, a graphically driven software system will be designed and developed at UKC to offer maximum facility for composites to be constructed. Tests will then be conducted with this on a sample population by our collaborators at Open under the guidance of participating polic forces. In particular, quantitative assessment will be made on the ability of subjects to build both simple synthetic composites (comprising a small number of components) and real faces, both known and unknown. The second phase of the project will explore the psych/mathematical convergence of the approach by both optimisation of the algorithmic procedure itself (via a simulated witness program) and the operational variables (field using human participants). A number of technical approaches will be explored including weighted PCA and Bayesian methods. Quantiative comparisons will be made between our system and existing composite technology such as E-FIT.
|
|
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: |
|
| Further Information: |
|
| Organisation Website: |
http://www.kent.ac.uk |