1 to 10 of 23 Results
Dec 8, 2022 - Ground truth data for HTR on South Asian Scripts
O'Neill, Alexander, 2022, "Ground Truth Model for Pracalit for Sanskrit and Newar MSS 16th to 19th C.", https://doi.org/10.11588/data/WI9184, heiDATA, V1
Ground truth data for a an OCR model. Will be continually updated. Originally trained on Transkribus with a PyLaia model created from ground truth data based on transcripts into Pracalit Unicode of four Nepalese manuscripts. The manuscripts used to create this model are Staatsbib... |
ZIP Archive - 479.7 MB -
MD5: 56e2cc32f0d0081fe109b596166f215f
|
Oct 26, 2022 - Ground truth data for HTR on South Asian Scripts
Merkel-Hilf, Nicole, 2022, "Ground Truth data for printed Devanagari", https://doi.org/10.11588/data/EGOKEI, heiDATA, V1
Ground truth (GT) data (jpg and alto xml files) for an OCR model that recognizes printed text in Devanagari script. The GT data was trained on Transkribus with the HTR+ engine. The training was performed on appr. 220 pages with appr. 27,000 words. The validation set was 10% of th... |
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 2.9 MB -
MD5: c3f5ea8ef80a5f18897fc503adff105e
|
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 19.7 MB -
MD5: 1a6729d60e255fbb367ac4625cf0ba9a
|
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 26.2 MB -
MD5: a60b4a3f543e2474e74812557f3bf188
|
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 10.4 MB -
MD5: 9c008fb50ceefbf637b725ea8aac357c
|
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 7.8 MB -
MD5: 85ea57e5e7a31e948ac00c6312119612
|
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 8.4 MB -
MD5: 0e0995442a6578cdbb4625d45fe39908
|
Oct 26, 2022 -
Ground Truth data for printed Devanagari
ZIP Archive - 7.2 MB -
MD5: b9b506915da67739eff6fbc1f9a55924
|