56 Commits (3941f2f17dc21242c3ce254b9c8218c616fbe394)

Author SHA1 Message Date
b-vr103 3941f2f17d gettin robust and doing sth for verticals 5 years ago
Gerber, Mike f90b3cfa86 🔊 sbb_textline_detector: In OCR-D interface, warn if overwriting existing segmentation 5 years ago
Gerber, Mike 11c0e9cee5 🐛 sbb_textline_detector: Do not print PAGE output to stdout
ocrd-sbb-textline-detector uses ocrd_page's parse() to parse XML input,
which writes the XML to stdout by default.

Fix this by silencing it using parse()'s silence=True.
5 years ago
wrznr 4fc57d7756 Assign page id 5 years ago
wrznr 9e9163e852 Simplify the iteration over files in the input file group 5 years ago
Mike Gerber 6e0decb5ec
Merge pull request #12 from kba/rename-tool
Rename ocrd_sbb.. to ocrd-sbb... in ocrd_cli.py, ht @bertsky
5 years ago
Gerber, Mike 5fb30a7a1f Revert "Merge branch 'master' of https://github.com/qurator-spk/sbb_textline_detector"
This reverts commit 417b9235d5, reversing
changes made to a74974b7b6.
5 years ago
Konstantin Baierer cf6381c148 Rename ocrd_sbb.. to ocrd-sbb... in ocrd_cli.py, ht @bertsky 5 years ago
Clemens Neudecker 51e241fd84
Merge pull request #5 from cneud/cneud-fix-typos
Fix typos
5 years ago
Clemens Neudecker 12c07f389d
Merge pull request #7 from cneud/cneud-fix-docstring
fix docstring
5 years ago
Clemens Neudecker 29870f26e1
Merge pull request #4 from cneud/cneud-PAGE2019
PAGE2019
5 years ago
Konstantin Baierer b6ca1a7c53 kebab-case snake_case executable, fix #9 5 years ago
Clemens Neudecker 6c0bfba686
fix typos 5 years ago
Clemens Neudecker c8bc468628
fix docstring 5 years ago
Clemens Neudecker e696a068cb
Fix typos 5 years ago
Clemens Neudecker d90dad48fd
PAGE2019 5 years ago
Rezanezhad, Vahid 19116091f9 Update config_params.json 5 years ago
Gerber, Mike af5cbe9052 🐛 sbb_textline_detector: Fix making the output file id 5 years ago
Rezanezhad, Vahid 2112bb18c6 fixed the bug: local variable 't4' referenced before assignment 5 years ago
Rezanezhad, Vahid a11f6740cb Update main.py - robust deskewing and better page extraction 5 years ago
Rezanezhad, Vahid 0182b7087f remove multiprocessing bug 5 years ago
Gerber, Mike 8fa7179560 🐛 sbb_textline_detector: Disable multiprocessing to fix race condition
Lines were sorted in the wrong regions. Work around this by disabling
multiprocessing until a proper fix is done.
5 years ago
Gerber, Mike 4aed06a325 sbb_textline_detection: Preserve input PAGE info by merging segmentation results
ocrd_sbb_textline_detection used the output XML by main.py as is, and
– by doing this – threw away any input data from the input PAGE,
including the critical pc:AlternativeImage and the less important
pc:MetadataItem.

Fix this by merging the segmentation results into a file created from
the input file.

Also add a pc:MetadataItem processingStep about the segmentation
operation.
5 years ago
Gerber, Mike 4fb3e70ef6 🧹 sbb_textline_detector: Do not create empty/space-only TextEquivs (again) 5 years ago
Gerber, Mike bf41a29e7b 🐛 sbb_textline_detector: Do not hardcode Created/LastChange elements 5 years ago
Gerber, Mike fbd21cdb81 🧹 sbb_textline_detector: Do not create empty/space-only TextEquivs (again) 5 years ago
Rezanezhad, Vahid 2d6dd92b31 Update main.py 5 years ago
Rezanezhad, Vahid 9f97f34255 Update main.py 5 years ago
Rezanezhad, Vahid 8c954a6c7a Update main.py 5 years ago
Rezanezhad, Vahid 6714481556 Update main.py 5 years ago
Rezanezhad, Vahid 719824f19d Update main.py 5 years ago
Gerber, Mike f94511a1d8 Merge branch 'master' of code.dev.sbb.berlin:qurator/mono-repo 5 years ago
Gerber, Mike 4f28cd905a 🧹 sbb_textline_detector: Do not create empty/space-only TextEquivs
ocrd_tesserocr or ocrd_cis complain about already existing text if
empty/space-only TextEquivs elements exist after segmentation. Also, it
does not make sense to create them in a segmentation step.

Fix by removing the code generating the elements.
5 years ago
Rezanezhad, Vahid 00929ab391 Update main.py 5 years ago
Gerber, Mike f0dd955606 Merge branch 'master' of code.dev.sbb.berlin:qurator/mono-repo 5 years ago
Gerber, Mike 2528573b4f sbb_textline_detector: Allow PAGE input in OCR-D interface
Previous OCR-D processors may output PAGE files instead of image files.
Resolve images file from PAGE files if necessary.
5 years ago
Rezanezhad, Vahid d8e04e3de4 memory leakage is removed. New deskewing methid is integrated. 5 years ago
Rezanezhad, Vahid 47d972b459 Update main.py 5 years ago
Gerber, Mike 103cfa0565 Merge branch 'master' of code.dev.sbb.berlin:qurator/mono-repo 5 years ago
Gerber, Mike 7884ab93c6 🧹 sbb_textline_detector: Destroy Keras session at the end of a run() to free up memory 5 years ago
Gerber, Mike 5d440857e7 🧹 sbb_textline_detector: Delete textline session/model after using it 5 years ago
cneud 4201fa7d0f sbb_textline_detector: typo (polugons --> polygons) 5 years ago
Gerber, Mike 9b2c415125 🐛 sbb_textline_detector: Use the correct image filename in the output PAGE 5 years ago
Rezanezhad, Vahid 1702472401 Update main.py 5 years ago
Rezanezhad, Vahid ca9f47eb20 Update main.py 5 years ago
Rezanezhad, Vahid 419beed836 Update main.py 5 years ago
Gerber, Mike 2199bf0d8c 🧹 sbb_textline_detector: Remove extra .xml suffix from METS file id 5 years ago
Gerber, Mike b4bef6460c 🐛 sbb_textline_detector: Use the correct image filename in the output PAGE 5 years ago
Gerber, Mike 1c7d45d3d0 ♻ sbb_textline_detector: Remove redundant and wrongly named parameter dir_of_image 5 years ago
Gerber, Mike d5a020fb3a 🧹 sbb_textline_detector: Remove debug print()s 5 years ago