Deep Bayesian Self-Training
- Submitting institution
-
University of Lincoln
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 36321
- Type
- D - Journal article
- DOI
-
10.1007/s00521-019-04332-4
- Title of journal
- Neural Computing and Applications
- Article number
- -
- First page
- 4275
- Volume
- 32
- Issue
- 9
- ISSN
- 0941-0643
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2019
- URL
-
http://doi.org/10.1007/s00521-019-04332-4
- 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
-
5
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper is a novel research outcome of the Machine Learning Group, in collaboration with Laboratory of Vision Engineering, National Centre for Food Manufacturing and OAL Company. We developed Deep Learning systems that detect existence of correct use-by date in food packaging photos taken as the products pass along food production lines (ICIP 2018, http://eprints.lincoln.ac.uk/id/eprint/31978/, Signal_ Image_ and_Video Processing 2020, https://doi.org/10.1007/s11760-020-01764-7). We provided measures of uncertainty in DNN decision making over non-annotated datasets, also developing and applying domain adaptation (Computers in Industry, https://doi.org/10.1016/j.compind.2020.103293). We co-developed OAL’s date code verification, AI-enabled vision system, APRIL™ Eye, https://connected.oalgroup.com/faq/april-eye-launch, https://youtu.be/7n868Vj3_AQ, https://connected.oalgroup.com/april-eye, https://www.oalgroup.com/news1/double-win-for-oal-at-ppma-2018.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -