-
cc7504ea33
🔍 Try uploading our XML to check it
Gerber, Mike
2020-02-26 11:59:56 +0100
-
20310d454a
🔍 Try uploading our XML to check it
Gerber, Mike
2020-02-25 19:29:22 +0100
-
90188c37cb
⚡ Download tessdata_best from qurator-data.de mirror
Gerber, Mike
2020-02-25 18:33:59 +0100
-
007d26df87
🚧 Install olena via preliminary Ubuntu package
Gerber, Mike
2020-02-25 18:33:16 +0100
-
8462112863
📝 README: **test environment**
Mike Gerber
2020-02-21 16:59:35 +0100
-
8177aab29f
📝 README: Mention historical prints
Gerber, Mike
2020-02-21 16:57:22 +0100
-
dcbdefc16e
📝 README: Describe what this does and why
Gerber, Mike
2020-02-21 16:54:10 +0100
-
abc207d655
📝 README: Include example workspace + reference PAGE Viewer and dinglehopper
Gerber, Mike
2020-02-21 13:21:06 +0100
-
8cd842419d
⬆ Update ocrd_tesserocr to fix glyph bug (OCR-D/ocrd_tesserocr#112)
Gerber, Mike
2020-02-17 18:52:44 +0100
-
2f10596d28
⬆ Update qurator_data_lib.sh (Fixes GH-5)
Gerber, Mike
2020-02-13 19:02:57 +0100
-
c92b10b984
🚧 qurator_data_lib.sh: Do not hardcode data/
Gerber, Mike
2020-02-13 18:19:49 +0100
-
58282c9e95
✨ Include glyph output
Gerber, Mike
2020-02-13 16:13:24 +0100
-
11a30892c5
🔍 Only do pip3 list when LOG_LEVEL >= DEBUG
Gerber, Mike
2020-02-13 15:02:15 +0100
-
9f111ca362
🧹 Do not validate OCR results twice
Gerber, Mike
2020-02-12 18:08:11 +0100
-
8ca25f3c56
🎨 Expose OCR textequiv_level as a environment variable
Gerber, Mike
2020-02-12 14:48:22 +0100
-
0cb0e35e8e
⬆ Update ocrd_calamari to 0.0.5
Gerber, Mike
2020-02-12 14:28:04 +0100
-
868ac5774c
🎨 Improve structure and documentation of run
Gerber, Mike
2020-02-11 15:51:56 +0100
-
979c7044a8
✨ Make OCR-D-IMG-BIN output group explicit
Gerber, Mike
2020-02-11 14:26:53 +0100
-
2b93fe3400
👷 qurator_data_lib.sh: Check that we are running bash
Gerber, Mike
2020-02-11 14:15:32 +0100
-
28bb482ceb
✨ Produce word results
Gerber, Mike
2020-02-10 19:26:04 +0100
-
6ae85063c5
📝 Document do_validate() options better
Gerber, Mike
2020-02-10 19:25:08 +0100
-
1252d8ccc3
🎨 Nudge build+download towards the standard qurator_data_lib.sh
Gerber, Mike
2020-02-10 19:23:17 +0100
-
61bb4f99f6
✅ Travis: Add status badge
Gerber, Mike
2020-02-10 18:01:25 +0100
-
8a92556afd
✅ Travis: Check OCR results
Gerber, Mike
2020-02-10 17:54:52 +0100
-
d64713f5b6
Merge branch 'master' of https://github.com/mikegerber/my_ocrd_workflow
Gerber, Mike
2020-02-10 17:05:02 +0100
-
-
bb92f8b1e6
🧹 Remove half-ass GPU support to fix Travis build
Gerber, Mike
2020-02-10 17:04:09 +0100
-
c8a64e5d57
🐛 Fix textline_detection model download
Gerber, Mike
2020-02-10 15:46:55 +0100
-
-
a097532847
🐛 select+do is apparently a bash feature, so make ./build a bash script
Gerber, Mike
2020-02-10 15:12:27 +0100
-
db8a6f6a0b
✅ Travis: Avoid trying to checkout private data/ submodule
Gerber, Mike
2020-02-10 15:04:41 +0100
-
7d17b9b2d4
✅ Add initial Travis configuration
Gerber, Mike
2020-02-10 15:00:56 +0100
-
788aedcb9b
⬆ Update sbb_textline_detector (just README changes)
Gerber, Mike
2020-02-10 14:40:17 +0100
-
934814c03c
🐳 Docker: Comment installing requirements
Gerber, Mike
2020-02-10 14:39:21 +0100
-
6d5305d07b
🧹 Docker: Move textline_detection model copy to the other OCR model copies
Gerber, Mike
2020-02-10 14:37:23 +0100
-
041cee707e
🧹 Remove unused vendor/sbb_tetline_detector tar (Fixes GH-3)
Gerber, Mike
2020-02-10 13:47:34 +0100
-
0889d1a5e3
🧹 Update/move some XXXs/TODOs
Gerber, Mike
2020-02-07 19:42:54 +0100
-
b08dc66f9f
🐳 Docker: Consistently use trailing slash when copying a file to a directory
Gerber, Mike
2020-02-07 19:37:31 +0100
-
2cf68f149d
♻ Extract a main() function for the main stuff
Gerber, Mike
2020-02-07 18:57:46 +0100
-
be0a0c353a
📝 Document the two remaining un-documented functions
Gerber, Mike
2020-02-07 18:47:16 +0100
-
848dd143fd
🎨 Use long command lines again
Gerber, Mike
2020-02-07 18:46:33 +0100
-
6b83d5ae1e
🧹 Update/move some XXXs/TODOs
Gerber, Mike
2020-02-07 18:01:26 +0100
-
98aee51801
🔧 Set up logging level using /etc/ocrd_logging.py instead of "-l"
Gerber, Mike
2020-02-07 17:51:53 +0100
-
5a55598d0c
🧹 Remove image reference fixing remnants - jpageviewer now has --resolve-dir
Gerber, Mike
2020-02-07 17:51:44 +0100
-
44979e7fa2
🧹 do_linesegmentation_sbb: It's now clear that sbb segmentation works with RGB images
Gerber, Mike
2020-02-07 17:50:33 +0100
-
460b6c34d1
✏ Fix typo in $ocrd_olena_binarize_parameters
Gerber, Mike
2020-02-07 17:20:48 +0100
-
71d54c6978
🔧 Set up logging level using /etc/ocrd_logging.py instead of "-l"
Gerber, Mike
2020-02-07 17:12:51 +0100
-
1a538dce1a
🧹 Remove superfluous mets.xml options
Gerber, Mike
2020-02-07 16:25:40 +0100
-
c192bfdbfe
🧹 Remove workaround for TEMP/ directory bug
Gerber, Mike
2020-02-07 14:44:48 +0100
-
d7a2aac44b
♻ Remove file groups using "ocrd workspace remove-group"
Gerber, Mike
2020-02-07 14:26:20 +0100
-
c8039db686
🎨 Put validate options into a variable
Gerber, Mike
2020-02-07 14:13:32 +0100
-
5ece7f1b0a
🧹 Remove remnants of ocrd-ocropy-segment
Gerber, Mike
2020-02-07 14:01:53 +0100
-
135489eaeb
🧹 Remove page_downgrade_to_2018
Gerber, Mike
2020-02-07 13:59:55 +0100
-
423d9c2ed6
🚧 do_validate: Skip dimension checking
Gerber, Mike
2020-02-07 13:59:19 +0100
-
377cf1dcab
🧹 Remove ocrd_kraken dep
Gerber, Mike
2020-02-07 13:34:32 +0100
-
948e9074df
⬆ Update to ocrd_calamari 0.0.4
Gerber, Mike
2020-02-07 13:31:26 +0100
-
1ef850992c
🎨 Use same style of specifying parameters for all processors
Gerber, Mike
2020-02-07 13:20:18 +0100
-
b468d688f2
🧹 Remove font identification for now
Gerber, Mike
2020-02-07 12:27:42 +0100
-
07555e8270
🎨 Use new OCR-D JSON string parameters
Gerber, Mike
2020-02-07 12:24:51 +0100
-
2a14d21925
🔥 Replace pipdeptree call with "pip3 check"
Gerber, Mike
2020-02-07 12:21:43 +0100
-
e860549109
🐛 Upgrade pip before using it (technically we have done it before)
Gerber, Mike
2020-02-07 12:21:04 +0100
-
98dd7d2e67
🐛 Upgrade pip before using it by way of ocrd_olena install
Gerber, Mike
2020-02-07 12:20:15 +0100
-
1a20fe8f38
Add work around concurrency problems
RobinSchaefer
2020-02-04 16:51:38 +0100
-
9c31d604e9
⬆ Update ocrd-sbb-textline-detector command
Gerber, Mike
2020-01-16 16:34:03 +0100
-
fd56731464
🚧 Do not check PAGE coordinates for now
Gerber, Mike
2020-01-16 16:33:36 +0100
-
87a2bce93c
⬆ Update calamari-models URL + path
Gerber, Mike
2020-01-16 15:44:26 +0100
-
2b8c6728bc
⬆ Update model URL
Gerber, Mike
2020-01-15 17:31:44 +0100
-
71d1ed0a4c
⬆ Update sbb_textline_detector
Gerber, Mike
2019-11-28 17:48:12 +0100
-
6e3b4e707a
💩 Mark textline_detection tar for update
Gerber, Mike
2019-11-28 17:26:12 +0100
-
03badaf887
⬆ Update sbb_textline_detector
Gerber, Mike
2019-11-28 16:38:41 +0100
-
d166077a55
✨ Update to sbb_textline_detector with the fixed AlternativeImage support (= merged PAGE results)
Gerber, Mike
2019-11-20 12:40:05 +0100
-
de47a3e5b1
🔥 Remove now unused page_fix_image_references()
Gerber, Mike
2019-11-20 12:39:02 +0100
-
eb58448f6d
🎡 Check pip dependencies early
Gerber, Mike
2019-11-19 14:35:23 +0100
-
3ecf478f79
⬆ Update sbb_textline_detector/ocrd_calamari
Gerber, Mike
2019-10-31 18:21:17 +0100
-
edd0930952
⚙ Download files from the web
Gerber, Mike
2019-10-31 15:22:12 +0100
-
21df393b0f
⚙ Suggest commands to fix data submodule
Gerber, Mike
2019-10-31 12:41:03 +0100
-
cd2e92fbc4
⚙ Give use choice to fix data sub-dir
Gerber, Mike
2019-10-31 11:32:37 +0100
-
eeb733486f
⚙ Sanity-check data submodule
Gerber, Mike
2019-10-30 17:54:05 +0100
-
1af18c629e
🧹 Validate imagefilename again
Gerber, Mike
2019-10-30 11:25:34 +0100
-
c994be2efb
🐛 Remove obsolete Pillow==5.4.1 dependency (fixes setup)
Gerber, Mike
2019-10-30 11:13:08 +0100
-
34b34fc84f
🐛 Do not run as root
Gerber, Mike
2019-10-30 11:12:11 +0100
-
6ad8d50552
⬆ Update sbb_textline_detector
Gerber, Mike
2019-10-30 11:11:24 +0100
-
2a6df526b5
⬆ Update sbb_textline_detector
Gerber, Mike
2019-10-22 17:58:03 +0200
-
de49aa715b
⬆ Update to OCR-D 1.0.0
Gerber, Mike
2019-10-21 17:04:49 +0200
-
7025d960b4
✨ Use ocrd_olena for binarization
Gerber, Mike
2019-10-21 17:04:06 +0200
-
63c364207c
💩 Add a funny workaround to get git-annex to give us our files
Gerber, Mike
2019-10-18 16:32:31 +0200
-
33e25641f2
⬆ Update sbb_textline_detector
Gerber, Mike
2019-10-18 13:22:47 +0200
-
2b67f5feb4
⬆ Update sbb_textline_detector
Gerber, Mike
2019-10-16 12:50:31 +0200
-
3687d6d7b4
🧹 Do not remove line confidences anymore
Gerber, Mike
2019-10-11 19:17:30 +0200
-
6454d20998
✨ Use sbb_textline_detector to segment lines
Gerber, Mike
2019-10-11 19:16:43 +0200
-
735e9599d7
🐛 ocrd-bugs: Most/All workspaces in bag files don't validate
Gerber, Mike
2019-10-09 13:36:54 +0200
-
0f8f1d814b
🐛 Mkdir robustly
Gerber, Mike
2019-10-07 12:36:40 +0200
-
bdab016e2c
✨ Use GT4HistOCR_2000000 model from qurator-data for Tesseract
Gerber, Mike
2019-10-02 16:48:28 +0200
-
57ff3fc19b
⬆ Update data
Gerber, Mike
2019-10-02 16:02:45 +0200
-
ff2cc50aed
⬆ Update dinglehopper (substitutions)
Gerber, Mike
2019-10-01 13:19:16 +0200
-
0c5ed94892
⬆ Update dinglehopper (to fix NFC trouble + substitutions)
Gerber, Mike
2019-10-01 11:30:00 +0200
-
1dde641d5a
⬆ Update dinglehopper (to fix text alignment)
Gerber, Mike
2019-09-30 18:26:12 +0200
-
47dd5d3b62
🎨 Move XML schemata to a better path
Gerber, Mike
2019-09-30 18:25:54 +0200
-
02457155aa
⬆ Update dinglehopper (to fix reading order)
Gerber, Mike
2019-09-30 16:10:13 +0200
-
af2034400a
🎨 Add extra newlines to separate steps
Gerber, Mike
2019-09-30 12:26:14 +0200
-
1863439d92
💩 Remove extra Pillow dependency workarounds
Gerber, Mike
2019-09-30 12:25:31 +0200
-
81b7e5458c
💩 Install Pillow 5.4.1 because pip does not have a dependency resolver
Gerber, Mike
2019-09-27 19:18:34 +0200