a22df11ebbRestoring the contour in the original image caused an error due to an empty tuple. This issue has been resolved, and as expected, the confidence score for this contour is set to zero
vahidrezanezhad
2025-04-14 00:42:08 +0200
e2907f67e0'from PIL.Image import Image' causes an error when using Image.new(), and since Image is already imported, this line can be safely commented out.
vahidrezanezhad
2025-04-06 00:33:36 +0200
132d3e3d27CI: use clash-free artifact name for report upload
Robert Sachunsky
2025-04-05 11:36:21 +0200
dc64079b6bCI: fix coverage report calls
Robert Sachunsky
2025-04-05 03:40:02 +0200
7609c64c8bCI: make coverage cfg work with both editable and dist install
Robert Sachunsky
2025-04-05 03:05:26 +0200
bbc06dbbc1CI: forgot to (re-)enable verbose logging
Robert Sachunsky
2025-04-05 02:10:52 +0200
2e3a29f66bIn light mode: To determine whether a main region is a header, I adjusted the ratio to achieve better results.
vahidrezanezhad
2025-04-04 15:36:31 +0200
Merge pull request #1 from bertsky/v3-api-refactor-init
Robert Sachunsky
2025-04-04 13:30:23 +0200
e9a4324b8fMerge branch 'v3-api-refactor-init' into bertsky-v3-api
kba
2025-04-04 13:14:12 +0200
38a2d60fa2Confidence value for textregions and in the case of not light version is set to zero. This is done to let the pipeline go through. It will be updated to return the correct value in upcomming commits
vahidrezanezhad
2025-04-03 12:47:27 +0200
Github Actions: free space: all existing Docker images
Robert Sachunsky
2025-04-01 00:23:53 +0200
4de441eaaaOCR prediction is now enabled to integrate results from both RGB and binarized images or to be performed on each individually
vahidrezanezhad
2025-03-31 21:28:05 +0200
b1da0a3327In OCR, the predicted text is now drawn on the image, and the results are saved in a specified directory. This makes it easier to review the predicted output
vahidrezanezhad
2025-03-31 18:43:14 +0200
Github Actions: free space more aggressively
Robert Sachunsky
2025-03-31 18:16:17 +0200
7430b57b65dockerfile: add smoke test
Robert Sachunsky
2025-03-31 16:56:47 +0200
f35f49376erun CLI test in TMPDIR, add ocrd-test
Robert Sachunsky
2025-03-31 16:55:57 +0200
ae066388eadocker: no need for g++, but install w/ 'EXTRAS=OCR'
Robert Sachunsky
2025-03-31 15:58:57 +0200
722b5c6bf1add make variable EXTRAS for optional dependencies
Robert Sachunsky
2025-03-31 15:58:12 +0200
c01609ff4eallow even more empty imports for optional dependencies
Robert Sachunsky
2025-03-31 15:57:22 +0200
51e9bfd6d7improve+extend dockerfile
Robert Sachunsky
2025-03-31 14:14:08 +0200
09248d4829improve+extend makefile
Robert Sachunsky
2025-03-31 14:13:16 +0200
46618f4229allow more empty imports for optional dependencies
Robert Sachunsky
2025-03-31 14:11:50 +0200
4be89910a2CLI: fix arg vs kwarg from merge
Robert Sachunsky
2025-03-31 02:38:24 +0200
9d61acf173simplify
Robert Sachunsky
2025-03-31 02:02:30 +0200
a1068ff2ebOCR-D: move sbb-binarize to ocrd-tool.json, update to v3
Robert Sachunsky
2025-03-31 01:47:32 +0200
c794d4d29fOCR-D: fix typo light_mode→light_version
Robert Sachunsky
2025-03-31 01:46:29 +0200
4338259ca1OCR-D: ensure page image gets replaced in result as well if not the original file
Robert Sachunsky
2025-03-31 01:17:14 +0200
55969b0173OCR-D: add docstring
Robert Sachunsky
2025-03-31 01:15:26 +0200
3916474b8bOCR-D: require >=v3.1
Robert Sachunsky
2025-03-31 01:15:12 +0200
6d02e90570OCR-D: restrict max_workers=1
Robert Sachunsky
2025-03-31 01:14:54 +0200
efd3fa6775allow empty imports for optional dependencies
Robert Sachunsky
2025-03-31 00:32:26 +0200
238132e260use 'image_filename' for pseudo-iteration outside 'dir_in' mode
Robert Sachunsky
2025-03-31 00:31:49 +0200
af4e2a4ffcdo not require 'dir_out' outside 'dir_in' mode
Robert Sachunsky
2025-03-31 00:31:09 +0200
ea136e3ddd'overwrite' check: only in 'dir_in' mode
Robert Sachunsky
2025-03-31 00:30:06 +0200
1f4a17b60dMerge remote-tracking branch 'origin/machine_based_reading_order_integration' into v3-api
Robert Sachunsky
2025-03-30 20:59:01 +0200
edf924c2cbocrd-tool: add dockerhub
Robert Sachunsky
2025-03-30 19:47:25 +0200
9b04688ebcThe rotate_image function has been updated. Additionally, the reading order is now correct in the case of the light version, provided that slope_deskew exceeds the slope_threshold.
vahidrezanezhad
2025-03-30 15:34:27 +0200
cf40f9ecc5The rotate_image function produces the exact same rotation as Imutils. Therefore, there is no need to retain the remove-imutils-1 branch.
vahidrezanezhad
2025-03-28 20:58:32 +0100
181c0c584fbbox rotation with opencv
cneud
2025-03-26 22:25:22 +0100
eaff9e3537Merge branch 'main' into remove-imutils-1
cneud
2025-03-26 20:16:46 +0100
7df0427b04In the context of OCR, if Page-XML files already contain text, the new predicted text will replace the existing text.
vahidrezanezhad
2025-03-26 18:42:06 +0100
370d44a66bSlope deskew in the light version is set to zero because when the slope_deskew value exceeds the slope_threshold, the reading order becomes incorrect. This issue needs to be addressed. Additionally, the textlines order within text region in the light version was reversed, and this has been corrected.
vahidrezanezhad
2025-03-26 10:45:34 +0100
4179a2ea3aintegrate binarization in ocrd-tool.json
cneud
2025-03-26 01:27:02 +0100
Konstantin Baierer 2025-04-22 13:24:12 +0200
vahidrezanezhad 2025-04-22 00:23:58 +0200
Clemens Neudecker 2025-04-17 17:01:20 +0200
kba 2025-04-16 19:27:17 +0200
Robert Sachunsky 2025-04-07 16:46:58 +0200
Robert Sachunsky 2025-04-06 18:24:56 +0000