Commit Graph

125 Commits (0462ae0b975f2d7827aeb7cf1648cab4e559e1d3)

Author SHA1 Message Date
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.
Konstantin Baierer 5d2fe79822 📦 v0.0.4
vahid 43c9302390 fixed and separators are also written in xml
Konstantin Baierer fce7cdfd8b 📦 v0.0.3
vahid aa2e91641a Merge branch 'main' of https://github.com/qurator-spk/eynollah into main
vahid 799a7c7632 fixed
Konstantin Baierer 26283c6a3b 📦 v0.0.2
vahid c4b2c71e68 resolving issue https://github.com/qurator-spk/eynollah/issues/38
vahid 7cbecadccc adding the binarization model and option to binarize input document for the cases like dark, stronly bright and other ones
vahid 44dad6a072 strong erosion, more modification
vahidrezanezhad 176c7531ab
Update eynollah.py
vahid c051e22432 fixing again the error raised because of erosion
vahidrezanezhad d5be8aece3
Merge pull request from qurator-spk/ocrd-cli
Ocrd cli
Konstantin Baierer 6c8852eb04 check_dpi: catch Pillow choking on faulty img, return 230
Konstantin Baierer ff265eee5c cv2pil: do COLOR_BGR2RGB conversion
Konstantin Baierer c7f304dcb6 ocrd processor: pass local filename as image_filename, ht @bertsky
Konstantin Baierer d0b0e23ac6 do DPI calculation as part of caching images
Konstantin Baierer ae0b4a825a ocrd cli: catch dpi == 1, return 230
Konstantin Baierer 2e8a3e3bee use Page.imageFilename directly for accurate DPI estimate
Konstantin Baierer 42ccb4711d
Update qurator/eynollah/ocrd-tool.json
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
vahid 1184d3d2fc issue raised by Clemens, strong erosion causing
Konstantin Baierer 4897cefdb7 allow passing PIL image to Eynollah w/o disk I/O
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>
Konstantin Baierer 1367f82605
improve ocrd-tool descriptions
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
vahidrezanezhad 037210b292
update writer.py
Konstantin Baierer b8d818ede1 writer: don't create empty PcGts at init
Konstantin Baierer 8c4e9b6068 allow passing pcgts to eynollah and writer
Konstantin Baierer 2bc34891a5 fix CLI call
vahid 98f9272c4b a trivial issue is resolved
Konstantin Baierer 9db6edf51e OCR-D CLI
Konstantin Baierer 1715f0d8b3 allow overriding DPI
Konstantin Baierer c95529725a 🐛 typo type{,_}
Konstantin Baierer 93f93444ee 🐛 typo {c,C}oords
Konstantin Baierer 416a84e542 replace lxml with OCR-D/core PAGE API
vahidrezanezhad 7a859ffae4
Merge branch 'main' into xml-rfct
vahidrezanezhad d5a9817390
back on track- freezing problem , memory error and issues with reading order by drop capitals and marginals are resolved
vahidrezanezhad 43b8759acf
back on track- freezing problem , memory error and issues with reading order by drop capitals and marginals are resolved
vahid b473c85a59 OOM error happend with tensorflow-gpu=1.15.5 is resolved
Konstantin Baierer 3d9da4feaa writer: use a single counter for all regions/lines
Konstantin Baierer a678bbf966 counter: add reset();
Konstantin Baierer a3465ca1a0 eliminate id_of_texts from xml_reading_order, fix plus one error
Konstantin Baierer 6c60d9e90a reading order: fix @index
Konstantin Baierer 02aa31cc66 Merge remote-tracking branch 'origin/main' into xml-rfct
Konstantin Baierer c5736e9b74 fix region counting
vahid 67a9fc8820 ..
vahidrezanezhad 4b3c8a6707
bug in reading order is fixed
vahidrezanezhad 73b7c780ab
Update eynollah.py
reading order bug for documents with text regions less than 5: fixed
Konstantin Baierer 03d75f5788 simplify serialize_lines_in_region
Konstantin Baierer d95fcf14c0 id_of_marginalia still necessary
Konstantin Baierer 56b688befe counter: allow arbitrary line/region id
Konstantin Baierer 7eb973b3aa xml_reading_order takes id_of_marginals directly
Konstantin Baierer 98568402c7 counter: init-overrideable
Konstantin Baierer 9b1da7c023 use counter for lines too
Konstantin Baierer 1cd3ee1a2e simplify calculate_polygon_coords
Konstantin Baierer 20fcac6232 remove unnecessary if
Konstantin Baierer 24da879844 add EynollahIdCounter class
Konstantin Baierer 9f5e4af5f0 factor out marginalia ID calc from xml_reading_order
Konstantin Baierer 630002d96d minor clean up xml_reading_order
Konstantin Baierer 38ab2aa573 eliminate tartib var
Konstantin Baierer 62fa710f27 move order_and_id_of_texts to utils.xml
Konstantin Baierer 8d4ce75656 typo s,teil,tile,g
Konstantin Baierer 18475b3c20 remaining typos idenitified by codespell
Konstantin Baierer adb96b5b49 s,hiearchy,hierarchy,g
Konstantin Baierer 10ae13f9b0 typo: s,separater,separator,
Konstantin Baierer 78a7ace863 typo: s,hirarchy,hierarchy,
Konstantin Baierer 526769354a typo: s,seperator,separator,
Konstantin Baierer ec9939c3c7 typo: s,hierachy,hierarchy,
Konstantin Baierer 6036478889 typo: s,enhancemnet,enhancement,g
Konstantin Baierer 5f2867bfcf typo: s,contoures,contours,g
Konstantin Baierer ccd83e94b1 typo: s,cprrsp,corresp,g
Konstantin Baierer 1f95a69bec typo: s,rotyate,rotate,g
Konstantin Baierer 375e9771e2 typo: s,spliter,splitter,g
Konstantin Baierer e332da34f6 typo: s,teil,tile,g
Konstantin Baierer b1b0e97945 typo: s,seperate,separate,g
Konstantin Baierer 58c4403e13 rename package to qurator.eynollah