|
|
6d44738c0f
|
⬆️ ocrd_calamari 1.0.5
|
2022-09-16 18:31:11 +02:00 |
|
|
|
42d3e8c9e7
|
🐛 ocrd-galley: Fix ocrd-eynollah-segment example
continuous-integration/drone/push Build is failing
|
2021-04-22 21:14:55 +02:00 |
|
|
|
b0ae5b9c6a
|
✨ ocrd-galley: Add support for ocrd-eynollah-segment
|
2021-04-22 21:11:49 +02:00 |
|
|
|
baddafa1ea
|
⬆️ Update ocrd_fileformat + use in default workflow to convert to ALTO
|
2021-02-04 17:36:55 +01:00 |
|
|
|
53d752f58d
|
🐛 Fix model path for ocrd_calamari 1.0
|
2020-12-04 13:13:52 +01:00 |
|
|
|
c1163405c4
|
🎨 s/pip3/pip/g
|
2020-11-19 18:25:10 +01:00 |
|
|
|
9e90ef08cd
|
📝 Add an example ALTO transformation to default workflow (Closes GH-34)
|
2020-11-16 14:46:18 +01:00 |
|
|
|
c23930c8df
|
✨ Add an example for ocrd-cis-ocropy-segment
|
2020-10-28 19:12:47 +01:00 |
|
|
|
0841af5491
|
🚧 Prepare supporting ocrd-sbb-binarize
ocrd-sbb-binarize seems to work but its input does not work with
ocrd-sbb-textline-detector:
https://github.com/qurator-spk/sbb_binarization/issues/8
https://github.com/qurator-spk/sbb_textline_detection/issues/47
|
2020-10-22 21:08:16 +02:00 |
|
|
|
568cf60b4c
|
⚙️ Consistently set LOG_LEVEL to INFO by default
|
2020-09-01 11:57:18 +02:00 |
|
|
|
17c6b15a1b
|
🐛 (Better) Handle missing pip3 in the main script
|
2020-08-24 18:13:13 +02:00 |
|
|
|
fc853d4d13
|
🐛 Handle missing pip3 in the main script
|
2020-08-24 17:23:28 +02:00 |
|
|
|
0b1da9a5db
|
🧹 Update Calamari model path
|
2020-08-05 20:13:14 +02:00 |
|
|
|
d1a2bfe669
|
🐛 Deal with ocrd_olena >= 1.2.0 using one output file group only
|
2020-07-31 14:25:35 +02:00 |
|
|
|
1a308a5522
|
🧹 Use OCR-D's -P, remove now redundant validation and remove now unnecessary functions
|
2020-07-30 20:55:11 +02:00 |
|
|
|
efd955c04f
|
🧹 Modernize my_ocrd_workflow and use OCR-D's new --overwrite
|
2020-07-30 20:20:52 +02:00 |
|
|
|
c5ae23d2ef
|
✨ Validate before even starting, to find data problems
|
2020-06-19 19:27:32 +02:00 |
|
|
|
a5b4e06a09
|
✨ Allow skipping validation
|
2020-03-09 16:50:30 +01:00 |
|
|
|
78f632a523
|
✨ Support --input-file-grp/-I command line parameter
|
2020-03-09 12:26:38 +01:00 |
|
|
|
58282c9e95
|
✨ Include glyph output
|
2020-02-13 16:13:24 +01:00 |
|
|
|
11a30892c5
|
🔍 Only do pip3 list when LOG_LEVEL >= DEBUG
|
2020-02-13 15:02:15 +01:00 |
|
|
|
9f111ca362
|
🧹 Do not validate OCR results twice
|
2020-02-12 18:08:11 +01:00 |
|
|
|
8ca25f3c56
|
🎨 Expose OCR textequiv_level as a environment variable
|
2020-02-12 14:48:22 +01:00 |
|
|
|
979c7044a8
|
✨ Make OCR-D-IMG-BIN output group explicit
|
2020-02-11 14:26:53 +01:00 |
|
|
|
28bb482ceb
|
✨ Produce word results
|
2020-02-10 19:26:04 +01:00 |
|
|
|
6ae85063c5
|
📝 Document do_validate() options better
|
2020-02-10 19:25:08 +01:00 |
|
|
|
2cf68f149d
|
♻ Extract a main() function for the main stuff
|
2020-02-07 18:57:46 +01:00 |
|
|
|
be0a0c353a
|
📝 Document the two remaining un-documented functions
|
2020-02-07 18:47:16 +01:00 |
|
|
|
848dd143fd
|
🎨 Use long command lines again
|
2020-02-07 18:46:33 +01:00 |
|
|
|
6b83d5ae1e
|
🧹 Update/move some XXXs/TODOs
|
2020-02-07 18:01:26 +01:00 |
|
|
|
5a55598d0c
|
🧹 Remove image reference fixing remnants - jpageviewer now has --resolve-dir
|
2020-02-07 17:51:44 +01:00 |
|
|
|
44979e7fa2
|
🧹 do_linesegmentation_sbb: It's now clear that sbb segmentation works with RGB images
|
2020-02-07 17:50:33 +01:00 |
|
|
|
460b6c34d1
|
✏ Fix typo in $ocrd_olena_binarize_parameters
|
2020-02-07 17:20:48 +01:00 |
|
|
|
71d54c6978
|
🔧 Set up logging level using /etc/ocrd_logging.py instead of "-l"
|
2020-02-07 17:12:51 +01:00 |
|
|
|
1a538dce1a
|
🧹 Remove superfluous mets.xml options
|
2020-02-07 16:25:40 +01:00 |
|
|
|
c192bfdbfe
|
🧹 Remove workaround for TEMP/ directory bug
|
2020-02-07 14:44:48 +01:00 |
|
|
|
d7a2aac44b
|
♻ Remove file groups using "ocrd workspace remove-group"
|
2020-02-07 14:26:20 +01:00 |
|
|
|
c8039db686
|
🎨 Put validate options into a variable
|
2020-02-07 14:13:32 +01:00 |
|
|
|
5ece7f1b0a
|
🧹 Remove remnants of ocrd-ocropy-segment
|
2020-02-07 14:01:53 +01:00 |
|
|
|
135489eaeb
|
🧹 Remove page_downgrade_to_2018
|
2020-02-07 13:59:55 +01:00 |
|
|
|
423d9c2ed6
|
🚧 do_validate: Skip dimension checking
|
2020-02-07 13:59:19 +01:00 |
|
|
|
948e9074df
|
⬆ Update to ocrd_calamari 0.0.4
|
2020-02-07 13:31:26 +01:00 |
|
|
|
1ef850992c
|
🎨 Use same style of specifying parameters for all processors
|
2020-02-07 13:20:18 +01:00 |
|
|
|
b468d688f2
|
🧹 Remove font identification for now
|
2020-02-07 12:30:39 +01:00 |
|
|
|
07555e8270
|
🎨 Use new OCR-D JSON string parameters
|
2020-02-07 12:24:51 +01:00 |
|
|
|
9c31d604e9
|
⬆ Update ocrd-sbb-textline-detector command
|
2020-01-16 16:34:03 +01:00 |
|
|
|
fd56731464
|
🚧 Do not check PAGE coordinates for now
|
2020-01-16 16:33:36 +01:00 |
|
|
|
87a2bce93c
|
⬆ Update calamari-models URL + path
|
2020-01-16 15:46:43 +01:00 |
|
|
|
d166077a55
|
✨ Update to sbb_textline_detector with the fixed AlternativeImage support (= merged PAGE results)
|
2019-11-20 12:40:05 +01:00 |
|
|
|
de47a3e5b1
|
🔥 Remove now unused page_fix_image_references()
|
2019-11-20 12:39:02 +01:00 |
|
