Published September 17, 2021
| Version 1.0
Dataset
Open
GoBo - A Handwriting Recognition dataset for Personalization
Authors/Creators
Description
This dataset comprises the images for the personalization described in the paper Personalizing Handwriting Recognition Systems with Limited User-Specific Samples.
Dataset Statistics (v.1.0)
* Handwritten word-level images
* English
* 40 Participants
* 5 sets from different sources for personalization
* 2 sets from 2 domains (same domains as 2 personalization sets) for testing
* 926 words/writer, 37k words in total
More details can be found on the Github Repository:
Github GoBo
Model
gobo_Baselinemodel.hdf5
Files
GoBo_v1-0.zip
Files
(285.2 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:9cef9b2be75935834f72e7b97dd78f67
|
66.4 MB | Download |
|
md5:ba25f9d9f1c8e71b94245dd597637236
|
218.8 MB | Preview Download |
Additional details
Related works
- Is published in
- Conference paper: https://link.springer.com/chapter/10.1007/978-3-030-86337-1_28 (URL)
- Is supplemented by
- https://github.com/catalpa-cl/GoBo/ (URL)