The multiscale bowler-hat transform for blood vessel enhancement in retinal images
- Submitting institution
-
University of Durham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 119070
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2018.10.011
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 739
- Volume
- 88
- Issue
- -
- ISSN
- 00313203
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2018
- URL
-
https://doi.org/10.1016/j.patcog.2018.10.011
- 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 - Innovative Computing
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We proposed a novel image informatics approach for multiscale vessel enhancement approach based on mathematical morphology. We evaluated the proposed method qualitatively and quantitatively, and compared it with the existing, state-of-the-art methods using both synthetic and real datasets. The proposed method achieves high-quality vessel-like structure enhancement in both synthetic examples and in clinically relevant retinal images, and is shown to be able to detect fine vessels while remaining robust at junctions. Its methodology is an important component of Procter & Gamble and The Rosetrees Trust grants focus on quantitative understanding of cellular networks.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -