An Efficient Self Organizing Active Contour Model for Image Segmentation
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D0030
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2014.07.052
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 820
- Volume
- 149
- Issue
- B
- ISSN
- 0925-2312
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- Year of publication
- 2015
- URL
-
https://www.sciencedirect.com/science/article/pii/S0925231214010042
- 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
- 40
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Self-Organising Active Contour (SOAC) is the proposed novel model, which has the unique ability to segment regions of interest in images with regions with intensity inhomogeneity (e.g., some types of medical images). To achieve high effectiveness, the proposed method uses Self-Organising Maps (SOM), and a novel formulation of the optimisation problem. SOAC has inspired more work in image segmentation using Active Contour Modelling (e.g. work in adopting deep learning methods has been based on findings of this paper: DOI: 10.14358/PERS.84.7.451). Experimentally using real and synthetic images, SOAC proved to be accurate, robust to different types of noise, and efficient.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -