Learning a Manifold of Fonts
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 146393553
- Type
- D - Journal article
- DOI
-
10.1145/2601097.2601212
- Title of journal
- ACM Transactions on Computer Systems
- Article number
- 91
- First page
- 1
- Volume
- 33
- Issue
- 4
- ISSN
- 0734-2071
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F2601097.2601212&file=a91-sidebyside.mp4&download=true
- 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
-
1
- Research group(s)
-
-
- Citation count
- 31
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work has a wide following in the typography community since it formulates the problem in the curve domain, rather than rasterizing fonts into the pixel domain, making the work much more applicable and producing high quality outputs. There are numerous examples of the online interactive demonstration being used as a case study for discussions on Machine Learning for Artists including organisations such as Unity Technologies and creative.ai. This work alignment and GPLVM combination has prompted subsequent works on statistical shape models for the creative industries (rotoscoping and motion capture) and medical imaging (bone segmentation and cell extraction).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -