qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-09 20:29:55 +02:00
Code Issues Projects Releases Wiki Activity
412 commits 13 branches 16 tags 16 MiB
Commit graph

153 commits

Author SHA1 Message Date
Gerber, Mike
11d9b00510 🧹 Don't produce spurious TextEquiv elements. 
eynollah produces spurious - and empy - pcGts TextEquiv elements. This
is a. unnecessary, b. wrong and c. produces a lot of warning messages
in subsequent OCR processing steps because the OCR processor warns
about already existing text.

Fix this by not generating any TextEquiv elements.

Fixes gh-37.
 2022-03-03 12:21:40 +01:00
Gerber, Mike
1fe8f92afc 🐛 Clarify message if an image was enhanced 2022-02-08 18:14:09 +01:00
Gerber, Mike
7ccd7663e1 💄 Improve more timing messages 2022-02-08 17:45:24 +01:00
Gerber, Mike
cdea0acffe 💄 Improve timing messages (Fixes #62) 2022-02-08 16:43:53 +01:00
Konstantin Baierer
f0ac0bb090 📦 v0.0.11 2022-02-02 12:05:06 +01:00
Konstantin Baierer
d75803b11d ocrd-tool: "models" parameter is a directory 2022-01-30 16:08:44 +01:00
Konstantin Baierer
e769f625fe 📦 v0.0.10 2021-09-27 14:31:23 +02:00
Konstantin Baierer
09d85bee87 Merge remote-tracking branch 'vahidrezanezhad/main' into main 2021-09-27 14:28:59 +02:00
vahidrezanezhad
169b50aaaf fixed: empty page error due None table contours 2021-09-23 15:51:30 -04:00
Konstantin Baierer
0e63ebcbe5 📦 v0.0.9 2021-08-16 17:36:37 +02:00
Konstantin Baierer
4223fed628 Merge remote-tracking branch 'vahidrezanezhad/main' into main 2021-08-16 17:30:33 +02:00
Konstantin Baierer
e7868b9851 📦 v0.0.8 2021-07-27 13:42:15 +02:00
Konstantin Baierer
5124a60527 set pcGtsId before adding file to mets 2021-07-27 13:05:57 +02:00
vahid
0859d22f4c modifications 2021-07-13 19:58:08 -04:00
vahid
14c588e162 resolving an issue 2021-07-13 10:12:18 -04:00
vahid
254abf4d3d more modifications for tables 2021-07-12 12:02:17 -04:00
vahid
b3b49272a5 README is updated 2021-07-10 07:28:31 -04:00
vahid
c67e155431 table detection completed, enhanced images can be now written to output 2021-07-09 10:23:45 -04:00
vahid
a5c940705a tables are integrated 2021-07-05 23:20:55 -04:00
vahid
80b17af40c #47 fixed 2021-07-05 18:49:45 -04:00
Konstantin Baierer
d784202ae1 📦 v0.0.7 2021-07-01 15:16:22 +02:00
Konstantin Baierer
6b810eb682 Merge remote-tracking branch 'vahidrezanezhad/main' into main 2021-07-01 15:11:50 +02:00
vahid
4560738427 #45 fixed 2021-07-01 08:46:17 -04:00
Konstantin Baierer
efc146feb8 📦 v0.0.6 2021-06-22 13:31:53 +02:00
vahid
becb0c1329 trivial 2021-06-21 10:06:16 -04:00
vahid
059905c9e4 #43 empty textlines caused by newer python-opencv, is resolved 2021-06-21 09:55:14 -04:00
vahid
d1330ffb80 #43 resolved 2021-06-21 05:22:00 -04:00
Konstantin Baierer
80795c9e6c 📦 v0.0.5 2021-05-19 11:42:45 +02:00
Konstantin Baierer
45939abdff OCR-D CLI: remove allow_enhancement parameter 
It does not toggle enhancement (eynollah does that internally anyway)
but setting it to true will base the coordinate calculations on that
enhanced (different-sized) image instead of the original. That is never
sensible in the OCR-D context.
 2021-05-18 19:00:51 +02:00
Konstantin Baierer
5d2fe79822 📦 v0.0.4 2021-05-18 13:59:19 +02:00
vahid
43c9302390 fixed #40 and separators are also written in xml 2021-05-12 07:29:05 -04:00
Konstantin Baierer
fce7cdfd8b 📦 v0.0.3 2021-05-11 13:15:25 +02:00
vahid
aa2e91641a Merge branch 'main' of https://github.com/qurator-spk/eynollah into main 2021-05-05 00:11:28 -04:00
vahid
799a7c7632 fixed #38 2021-05-05 00:11:00 -04:00
Konstantin Baierer
26283c6a3b 📦 v0.0.2 2021-05-04 18:12:21 +02:00
vahid
c4b2c71e68 resolving issue https://github.com/qurator-spk/eynollah/issues/38 2021-05-04 09:41:05 -04:00
vahid
7cbecadccc adding the binarization model and option to binarize input document for the cases like dark, stronly bright and other ones 2021-04-25 18:20:05 -04:00
vahid
44dad6a072 strong erosion, more modification 2021-04-23 13:48:21 -04:00
vahidrezanezhad
176c7531ab
Update eynollah.py 2021-04-22 11:01:58 -04:00
vahid
c051e22432 fixing again the error raised because of erosion 2021-04-22 11:02:32 -04:00
vahidrezanezhad
d5be8aece3
Merge pull request #33 from qurator-spk/ocrd-cli 
Ocrd cli
 2021-04-22 15:22:22 +02:00
Konstantin Baierer
6c8852eb04 check_dpi: catch Pillow choking on faulty img, return 230 2021-04-22 13:12:40 +02:00
Konstantin Baierer
ff265eee5c cv2pil: do COLOR_BGR2RGB conversion 2021-04-22 12:57:04 +02:00
Konstantin Baierer
c7f304dcb6 ocrd processor: pass local filename as image_filename, ht @bertsky 2021-04-22 12:31:00 +02:00
Konstantin Baierer
d0b0e23ac6 do DPI calculation as part of caching images 2021-04-22 12:07:14 +02:00
Konstantin Baierer
ae0b4a825a ocrd cli: catch dpi == 1, return 230 2021-04-22 10:28:01 +02:00
Konstantin Baierer
2e8a3e3bee use Page.imageFilename directly for accurate DPI estimate 2021-04-21 18:30:48 +02:00
Konstantin Baierer
42ccb4711d
Update qurator/eynollah/ocrd-tool.json 
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
 2021-04-21 10:55:28 +02:00
vahid
1184d3d2fc issue raised by Clemens, strong erosion causing 2021-04-18 17:59:18 -04:00
Konstantin Baierer
4897cefdb7 allow passing PIL image to Eynollah w/o disk I/O 2021-04-15 17:25:05 +02:00