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
340 commits 13 branches 16 tags 16 MiB
Commit graph

126 commits

Author SHA1 Message Date
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
Konstantin Baierer
d40c453dad
check_dpi: raise exception if resolution == 1 to trigger except clause 
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
 2021-04-14 17:42:37 +02:00
Konstantin Baierer
1367f82605
improve ocrd-tool descriptions 
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
 2021-04-14 17:31:57 +02:00
vahidrezanezhad
037210b292
update writer.py 2021-04-14 08:55:54 -04:00
Konstantin Baierer
b8d818ede1 writer: don't create empty PcGts at init 2021-04-14 10:53:32 +02:00
Konstantin Baierer
8c4e9b6068 allow passing pcgts to eynollah and writer 2021-04-14 10:38:07 +02:00
Konstantin Baierer
2bc34891a5 fix CLI call 2021-04-13 17:55:22 +02:00
vahid
98f9272c4b a trivial issue is resolved 2021-04-13 11:43:44 -04:00
Konstantin Baierer
9db6edf51e OCR-D CLI 2021-04-13 17:38:02 +02:00
Konstantin Baierer
1715f0d8b3 allow overriding DPI 2021-04-13 16:03:58 +02:00
Konstantin Baierer
c95529725a 🐛 typo type{,_} 2021-04-13 13:55:51 +02:00
Konstantin Baierer
93f93444ee 🐛 typo {c,C}oords 2021-04-13 13:55:31 +02:00
Konstantin Baierer
416a84e542 replace lxml with OCR-D/core PAGE API 2021-04-12 13:25:29 +02:00
vahidrezanezhad
7a859ffae4
Merge branch 'main' into xml-rfct 2021-04-07 12:34:23 -04:00
vahidrezanezhad
d5a9817390
back on track- freezing problem , memory error and issues with reading order by drop capitals and marginals are resolved 2021-04-07 11:35:42 -04:00
vahidrezanezhad
43b8759acf
back on track- freezing problem , memory error and issues with reading order by drop capitals and marginals are resolved 2021-04-07 11:34:35 -04:00
vahid
b473c85a59 OOM error happend with tensorflow-gpu=1.15.5 is resolved 2021-04-01 11:22:08 -04:00
Konstantin Baierer
3d9da4feaa writer: use a single counter for all regions/lines 2021-03-12 19:29:52 +01:00
Konstantin Baierer
a678bbf966 counter: add reset(); 2021-03-12 18:39:27 +01:00
Konstantin Baierer
a3465ca1a0 eliminate id_of_texts from xml_reading_order, fix plus one error 2021-03-11 19:44:42 +01:00
Konstantin Baierer
6c60d9e90a reading order: fix @index 2021-03-10 17:27:18 +01:00
Konstantin Baierer
02aa31cc66 Merge remote-tracking branch 'origin/main' into xml-rfct 2021-03-10 12:12:31 +01:00
Konstantin Baierer
c5736e9b74 fix region counting 2021-03-10 11:52:01 +01:00
vahid
67a9fc8820 .. 2021-03-09 08:55:19 -05:00
vahidrezanezhad
4b3c8a6707
bug in reading order is fixed 2021-03-09 08:33:37 -05:00
vahidrezanezhad
73b7c780ab
Update eynollah.py 
reading order bug for documents with text regions less than 5: fixed
 2021-03-09 08:20:33 -05:00
Konstantin Baierer
03d75f5788 simplify serialize_lines_in_region 2021-03-02 17:51:30 +01:00
Konstantin Baierer
d95fcf14c0 id_of_marginalia still necessary 2021-03-02 17:47:06 +01:00