Exploiting colour information for better scene text detection and recognition
- Submitting institution
-
Loughborough University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1930
- Type
- D - Journal article
- DOI
-
10.1007/s10032-015-0239-x
- Title of journal
- International Journal on Document Analysis and Recognition
- Article number
- -
- First page
- 153
- Volume
- 18
- Issue
- 2
- ISSN
- 1433-2833
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- 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
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The research impacted the state of the art in machine learning based text detection and recognition algorithms and was used to propose the novel design of Deep Neural Networks for Japanese Handwriting and Hand-drawn Object Recognition (EPSRC CDT-EI Studentship with Surface Intelligence Ltd., Oxford) and a Innovate UK R&D proposal (IUK Grant 22020, InkTracer, £223,684, Feb 2019) in collaboration with Surface Intelligence and WACOM (Japan). The project outcomes are soon to be exploited within WACOM’s Digital Ink workflows to recognise offline handwriting (Japanese, Chinese, English & Mathematical Expressions), generating revenue to Surface Intelligence.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -