Active appearance pyramids for object parametrisation and fitting
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 5866
- Type
- D - Journal article
- DOI
-
10.1016/j.media.2016.03.005
- Title of journal
- Medical Image Analysis
- Article number
- -
- First page
- 101
- Volume
- 32
- Issue
- -
- ISSN
- 1361-8415
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2016
- 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
-
3
- Research group(s)
-
A - Applied Computing
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in the premier journal in medical image analysis, this work advanced the state-of-the-art of appearance models fitting to medical imaging data, making it tractable for 3D data by leveraging multiscale representations (Local Feature Pyramids) for better spatial specificity and distinctiveness. The results on lumbar spinal stenosis grading were superior and had greater utility than produced concurrently ("SpineNet", Jamaludin et al., Oxford). This research has been used for hip impingement assessment in CT (Dickenson, UHCW), and has led to collaborative funding from the National Institute for Health Research for application to patella displacement and meniscal tear surgery (Ahmed et al.).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -