| EPSRC Reference: |
GR/M90665/01 |
| Title: |
NONLINEAR FEATURE DETECTION IN IMAGE DATABASES USING NEUTRAL NETWORKS |
| Principal Investigator: |
Kittler, Professor J |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Electronics & Physical Sciences |
| Organisation: |
University of Surrey |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
04 October 1999 |
Ends: |
03 October 2000 |
Value (£): |
17,829
|
| EPSRC Research Topic Classifications: |
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
The project will investigate nonlinear and adaptive methods of texture representation. In particular, we shall investigate feed forward neural networks and shared weight networks, adaptive filter banks, adaptive subspace self organising maps, and independent component analysis as means for texture representation. These alternatives will be implemented and compared with our standard approaches based on Gabor filters, wavelets, DCT coefficients. The comparative study will be carried out on an image database of several thousand frames compiled and used for our image/video database retrieval work. The performation characterisation will be carried out using a set of criteria reflecting the project objectives.
|
|
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 |