Seite - 117 - in Document Image Processing
Bild der Seite - 117 -
Text der Seite - 117 -
J. Imaging 2018,4, 43
intowords (Figure17).More thanone labelmaybegivento thecreatedword. Theorderofhoweach
character in thewordisselected isalsokept [21]. Balinese (Figure18)andtheSundanese (Figure19)
worddatasetwasmanuallyannotatedusingAletheia [63].
Table4.Palmleafmanuscriptdatasets forwordrecognitionandtransliterationtasks.
Manuscripts Train Test Text Published
Balinese 15,022 images
from130pages 10,475 images from
100pages Latin AMADI_LontarSet [17,25]
Khmer 16,333 images
(partof657pages) 7791 images (part
of657pages) LatinandKhmer SleukRithSet [21]
Sundanese 1427 images
from20pages 318 images from10
pages Latin SundaDataset [22]
Figure17.Khmerworddataset.
Figure18.Balineseworddataset.
Figure19.Sundaneseworddataset.
117
zurück zum
Buch Document Image Processing"
Document Image Processing
- Titel
- Document Image Processing
- Autoren
- Ergina Kavallieratou
- Laurence Likforman-Sulem
- Herausgeber
- MDPI
- Ort
- Basel
- Datum
- 2018
- Sprache
- deutsch
- Lizenz
- CC BY-NC-ND 4.0
- ISBN
- 978-3-03897-106-1
- Abmessungen
- 17.0 x 24.4 cm
- Seiten
- 216
- Schlagwörter
- document image processing, preprocessing, binarizationl, text-line segmentation, handwriting recognition, indic/arabic/asian script, OCR, Video OCR, word spotting, retrieval, document datasets, performance evaluation, document annotation tools
- Kategorie
- Informatik