Divergence of Gradient Convolution: Deformable Segmentation with Arbitrary Initializations
- Submitting institution
-
Swansea University / Prifysgol Abertawe
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 22242
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2015.2456503
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 3902
- Volume
- 24
- Issue
- 11
- ISSN
- 1941-0042
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- 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
-
-
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work reports a novel unified approach to deformable image segmentation that guarantees global optimum. To the best of our knowledge, this is the first reported work that achieves this level of initialisation independency with both local and global optimisation techniques. It provides great flexibility in data driven image segmentation, which is a significant improvement to one of the fundamental techniques in image processing. This flexibility provides new possibilities in object segmentation and application areas such as medical image analysis.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -