| EPSRC Reference: |
GR/S98528/01 |
| Title: |
Prevention is Better than Cure: Crime Prevention & Detection using in-depth Face Recognition - 2D+3D=ID |
| Principal Investigator: |
Kittler, Professor J |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Vision Speech and Signal Proc CVSSP |
| Organisation: |
University of Surrey |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
07 June 2004 |
Ends: |
06 December 2007 |
Value (£): |
292,661
|
| EPSRC Research Topic Classifications: |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Biometrics such as fingerprinting and DNA have contributed greatly to crime detection. Face recognition is an emerging technology that already plays a role in crime prevention by enabling effective access control to valuable resources. It has the potential to be even more important in areas such as recognition of offenders from public CCTV footage. A limitation of current systems is that they rely almost solely on 2D image data. These systems are sensitive to subject pose and illumination variations. We hypothesise that the use of 3D data and 3D face models integrated with current 2D face recognition methods can significantly improve recognition making it robust to pose and lighting change. This, together with new cheaper and more errective ways of deriving 3D, will enable the technique to be used in less constrained applications and greatly increase its use in crime related tasks.In this project we will collect 3D data sets (within the framework of existing benchmark standards that we have previously been influential in defining), we will develop new state of the art methods for extracting 3D from standard video (extending existing work on human modelling from video), we will develop means of using 3D models for pose correction and illumination normalisation and validate the advances both scientifically and with tests on a user defined, crime related scenario. A route for exploitation of the work is via OmniPerception, a University spin-off company that is pioneering the use of existing CVSSP work on 2D facial biometrics by porting it to smart cards. IBM have extensive interest and expertise in large scale security projects and will provide the project with user-oriented advice. PITO will provide strategic advice concerning how the methods could best be applied to typical policing tasks.
|
|
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.surrey.ac.uk |