Assembling convolution neural networks for automatic viewing transformation
- Submitting institution
-
Loughborough University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1978
- Type
- D - Journal article
- DOI
-
10.1109/tii.2019.2940136
- Title of journal
- IEEE Transactions on Industrial Informatics
- Article number
- -
- First page
- 587
- Volume
- 16
- Issue
- 1
- ISSN
- 1551-3203
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2019
- 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
-
4
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work leads to a fully automatic solution for the traditional image transformation problem via harnessing the power of artificial intelligence. This work is significant in that not only does it outperform the state-of-the-art methods by a large margin in terms of both accuracy and robustness, but it also offers a practically feasible way to improve the quality of distorted images. The technology has been successfully used by SukeIntel Company Ltd. (Yiqi Deng, yiqi_deng@163.com) in the project named "Video-based Object Detection and Counting Algorithms and Implementation" for viewing transformation.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -