On reducing the effect of covariate factors in gait recognition : a classifier ensemble method
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6056
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2014.2366766
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 1521
- Volume
- 37
- Issue
- 99
- ISSN
- 0162-8828
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2015
- URL
-
-
- 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
-
2
- Research group(s)
-
A - Applied Computing
- Citation count
- 66
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This highly cited paper, published in the top journal in the field, showed for the first time how an ensemble of weak classifiers that can exploit and reinforce the information provided by several corrupted gait features is able to classify individuals very accurately. This work has been taken up by experts working on people identification (e.g. Liu, Michigan State University; Yan, Microsoft AI & Research), palm recognition (Marcialis, University of Cagliari), and ensemble learning from noisy data (Yu, South China University of Technology). It was also pivotal in securing EU H2020 funding for the £1.4M RISE project IDENTITY.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -