Dynamical system approach for edge detection using coupled FitzHugh–Nagumo neurons
- Submitting institution
-
University of Southampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 20752613
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2015.2467206
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 5206
- Volume
- 24
- Issue
- 12
- ISSN
- 1057-7149
- Open access status
- Out of scope for open access requirements
- Month of publication
- August
- 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)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In this paper, we propose and rigorously analyse a novel approach for detecting edges in noisy images, using an analog, hardware-software hybrid design. This work formed the basis of the first author's PhD thesis. The work has been recognised in a comprehensive review on neuromorphic computing (https://arxiv.org/abs/1705.06963). Furthermore, Prasath et al. (2019) applied our algorithm and compared it to state-of-the-art edge detection algorithms in their extensive evaluation (doi:10.1109/TIP.2019.2924799). They showed that our algorithm is comparable to other algorithms for regular image edge detection tasks, even though the method’s original purpose was for hardware design (e.g., of a silicon retina).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -