Active contour based optical character recognition for automated scene understanding
- Submitting institution
-
University of the West of Scotland
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13039871
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2014.12.089
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 65
- Volume
- 161
- Issue
- -
- ISSN
- 0925-2312
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- 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
-
0
- Research group(s)
-
-
- Citation count
- 28
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This original work introduces a new mathematical framework (involving a new image-feature extraction and merging strategy which takes advantage of majority-vote and weighted-vote approaches) for optical character recognition. The framework has been fully implemented and evaluated over 4,500 images. The paper had an impact on the research community resulting the author being invited to deliver talks on this subject at major international conferences, e.g. IEEE-ICIP, IAPR-CAIP, IEEE-IROS, and to be a member of research networks EU-COST-IC1404 and EPSRC-ViiHM.
Moreover, some other researchers have also acknowledged the importance of this output in flagship journals (e.g. IEEE-TIP, Elsevier-ESWA).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -