Gerber, Mike
|
3687d6d7b4
|
🧹 Do not remove line confidences anymore
|
5 years ago |
Gerber, Mike
|
6454d20998
|
✨ Use sbb_textline_detector to segment lines
|
5 years ago |
Gerber, Mike
|
735e9599d7
|
🐛 ocrd-bugs: Most/All workspaces in bag files don't validate
|
5 years ago |
Gerber, Mike
|
0f8f1d814b
|
🐛 Mkdir robustly
|
5 years ago |
Gerber, Mike
|
bdab016e2c
|
✨ Use GT4HistOCR_2000000 model from qurator-data for Tesseract
|
5 years ago |
Gerber, Mike
|
57ff3fc19b
|
⬆ Update data
|
5 years ago |
Gerber, Mike
|
ff2cc50aed
|
⬆ Update dinglehopper (substitutions)
|
5 years ago |
Gerber, Mike
|
0c5ed94892
|
⬆ Update dinglehopper (to fix NFC trouble + substitutions)
|
5 years ago |
Gerber, Mike
|
1dde641d5a
|
⬆ Update dinglehopper (to fix text alignment)
|
5 years ago |
Gerber, Mike
|
47dd5d3b62
|
🎨 Move XML schemata to a better path
|
5 years ago |
Gerber, Mike
|
02457155aa
|
⬆ Update dinglehopper (to fix reading order)
|
5 years ago |
Gerber, Mike
|
af2034400a
|
🎨 Add extra newlines to separate steps
|
5 years ago |
Gerber, Mike
|
1863439d92
|
💩 Remove extra Pillow dependency workarounds
|
5 years ago |
Gerber, Mike
|
81b7e5458c
|
💩 Install Pillow 5.4.1 because pip does not have a dependency resolver
|
5 years ago |
Gerber, Mike
|
224762e1bb
|
🐛 Let ocrd_calamari handle the weird setuptools depencency
|
5 years ago |
Gerber, Mike
|
a272237bd8
|
⬆ Update ocrd dependency
|
5 years ago |
Gerber, Mike
|
2b9cab1a1a
|
⬆ Update ocrd_calamari
|
5 years ago |
Gerber, Mike
|
e5cd5b937e
|
✨ Run pip3 list for easier checking
|
5 years ago |
Gerber, Mike
|
bd24624bd7
|
⬆ Do not downgrade to PAGE 2018 anymore
|
5 years ago |
Gerber, Mike
|
0b2b66a0b4
|
🔧 Allow setting LOG_LEVEL
|
5 years ago |
Gerber, Mike
|
d6c38b5b9f
|
🧹 Do not install extra tesserocr
|
5 years ago |
Gerber, Mike
|
f19bba45b8
|
💩 Remove mysterious TEMP directory for now
|
5 years ago |
Gerber, Mike
|
68902f923d
|
📜 Downgrading to PAGE 2018 is not the last step anymore
|
5 years ago |
Gerber, Mike
|
6c0d7e0aee
|
💩 Do not fix PAGE image references for now
|
5 years ago |
Gerber, Mike
|
e3bf65b502
|
⬆ Update dinglehopper
|
5 years ago |
Gerber, Mike
|
87968cd297
|
🧹 README: Move TODO to my usual TODO list
|
5 years ago |
Gerber, Mike
|
debecf71b9
|
💩 Install the right Pillow version manually...
|
5 years ago |
Gerber, Mike
|
a3d6befb0d
|
🏗 Build Tesseract from source
|
5 years ago |
Gerber, Mike
|
d903e3634c
|
📝 README: Clarify workspace TODO
|
5 years ago |
Gerber, Mike
|
8a04602044
|
📝 README: Not using podman anymore
|
5 years ago |
Gerber, Mike
|
0782dbde32
|
⬆ Update dinglehopper
|
5 years ago |
Gerber, Mike
|
343a3fbf82
|
🔧 Evaluate both Tesseract and Calamari results
|
5 years ago |
Gerber, Mike
|
0bc06c2fad
|
✨ Run Calamari OCR
|
5 years ago |
Gerber, Mike
|
001e62f54a
|
🔧 Use docker, not podman
|
5 years ago |
Gerber, Mike
|
daed87566e
|
🚑 Don't install typegroups classifier for now
|
5 years ago |
Gerber, Mike
|
d8f3438ac5
|
🚑 Don't check pixel density
|
5 years ago |
Gerber, Mike
|
b169f35bb1
|
🔧 Build container with cache again
|
5 years ago |
Gerber, Mike
|
85ff80d548
|
✨ Use dinglehopper's new OCR-D interface
|
5 years ago |
Gerber, Mike
|
d5aa273b44
|
🚧 Use ocr-eval aka dinglehopper
|
5 years ago |
Gerber, Mike
|
be5750f4e1
|
✨ As a last step, downgrade to PAGE 2018 to support PAGE Viewer
|
5 years ago |
Gerber, Mike
|
cf2b4de2a0
|
🧹 Validate again after fixing image references
|
5 years ago |
Gerber, Mike
|
21e00932be
|
🐛 Use a valid filegrp USE for fontident
|
5 years ago |
Gerber, Mike
|
ade39a278c
|
🎨 Align file groups
|
5 years ago |
Gerber, Mike
|
3fee2d4fe6
|
📌 Use my ocrd_typegroups_classifier fix for passing down the page id
|
5 years ago |
Gerber, Mike
|
44772f1923
|
🚧 Work around problems with ocrd-tesserocr producing TextEquiv/@conf
|
5 years ago |
Gerber, Mike
|
8b67866aac
|
✨ Validate PAGE XML after OCR
|
5 years ago |
Gerber, Mike
|
0d7fd21446
|
✨ Validate workspace after each step
|
5 years ago |
Gerber, Mike
|
d37db86da1
|
📌 Use my ocrd_kraken fix for passing down the page id
|
5 years ago |
Gerber, Mike
|
4addde2e19
|
Use PAGE 2019
|
5 years ago |
Gerber, Mike
|
de841746e3
|
Use PAGE 2019
|
5 years ago |