Self-organizing hierarchical particle swarm optimization of correlation filters for object recognition
- Submitting institution
-
University of Sussex
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9832_70957
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2017.2762354
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 24495
- Volume
- 5
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2017
- URL
-
https://doi.org/10.1109/ACCESS.2017.2762354
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
7
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Maximum average correlation filters have been developed that improve intra-class tolerance with inter-class discrimination, whilst maintaining resistance to background clutter. However, their performance is task dependant and sensitive to the choice of values for three parameters. These have been chosen in a largely ad hoc manner for given tasks. This paper reports the use of heuristic methods based on the particle swarm technique, and a hierarchical enhancement of this method, to determine suitable values of these parameters. Quantitative assessment of the resulting filter performance demonstrates significant improvements from the choice of the filter parameters selected by this method. User Pakistan-MOD
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
