276 commits

Author	SHA1	Message	Date
Robert Sachunsky	235539a350	filter_contours_without_textline_inside: avoid removing from identical lists twice	2025-09-29 17:47:51 +02:00
Robert Sachunsky	11e143afee	polygon2contour: avoid overflow	2025-09-29 17:47:51 +02:00
Robert Sachunsky	7a9e8256ee	increase dilatation: textregions/lines (5→6), seplines (0→1)	2025-09-29 17:47:51 +02:00
Robert Sachunsky	f3faa29528	refactor shapely converisons into contour2polygon / polygon2contour, also handle heterogeneous geometries	2025-09-29 17:47:51 +02:00
Robert Sachunsky	0650274ffa	move dilate_*_contours to .utils.contour, rename dilate_textregions_contours_textline_version → dilate_textline_contours	2025-09-29 17:47:47 +02:00
Robert Sachunsky	a433c73628	filter_contours_area_of_image*: also ensure validity here	2025-09-29 17:46:50 +02:00
Robert Sachunsky	17bcf1af71	rename *lines_xml → *seplines for clarity	2025-09-29 17:46:50 +02:00
Robert Sachunsky	e730725da3	check_any_text_region_in_model_one_is_main_or_header_light: return original instead of resampled contours	2025-09-29 17:46:50 +02:00
Robert Sachunsky	7b51fd6624	avoid creating invalid polygons via rounding	2025-09-29 17:46:50 +02:00
Robert Sachunsky	41cc38c51a	get_textregion_contours_in_org_image_light: no back rotation, drop slope_first (always 0)	2025-09-29 17:46:48 +02:00
Robert Sachunsky	afba70c920	separate_lines/do_work_of_slopes: skip if crop is empty	2025-09-29 17:44:39 +02:00
Robert Sachunsky	66b2bce8b9	return_boxes_of_images_by_order_of_reading_new: log any exceptions	2025-09-29 17:44:36 +02:00
Robert Sachunsky	b48c41e68f	return_boxes_of_images_by_order_of_reading_new: simplify, avoid changing dtype during np.append	2025-09-29 17:42:53 +02:00
Robert Sachunsky	09ece86f0d	dilate_textregions_contours: simplify (via shapely's Polygon.buffer()), ensure validity	2025-09-29 17:42:53 +02:00
kba	6ea6a62801	📝 v0.5.0	2025-09-26 16:23:46 +02:00
Robert Sachunsky	480daa4c7c	test_run: make ocr -doit work (add truetype file)	2025-09-25 22:28:15 +02:00
kba	f37d80c188	Merge branch 'adapt-ocrd' of https://github.com/qurator-spk/eynollah into adapt-ocrd	2025-09-25 21:39:55 +02:00
kba	57ee1cdc72	Merge remote-tracking branch 'bertsky/mbro_dead_code-plus-fixes-plus-tests' into adapt-ocrd	2025-09-25 21:39:36 +02:00
kba	9303ded11f	ocrd-tool.json: use models_layout instead of eynollah_layouts for consistency	2025-09-25 21:12:52 +02:00
Robert Sachunsky	7c79902835	enhancement/mbreorder: make all path options kwargs to run() instead of attributes	2025-09-25 20:51:02 +02:00
kba	11de8a025d	Adapt ocrd-eynollah-segment for release	2025-09-25 20:11:48 +02:00
kba	5e15c4f248	Merge remote-tracking branch 'bertsky/mbro_dead_code-plus-fixes-plus-tests' into prepare-release-v0.5.0	2025-09-25 20:05:03 +02:00
Robert Sachunsky	2d14d57e4f	ocr: minimal debug logging	2025-09-25 19:52:50 +02:00
Robert Sachunsky	1dcc7b5795	ocr CLI: make --model vs --model_name xor	2025-09-25 16:38:43 +02:00
Robert Sachunsky	5b1e0c1327	layout/ocr: make all path options kwargs to run() instead of attributes; ocr: drop redundant prediction_with_both_of_rgb_and_bin in favour of just bool(dir_in_bin)	2025-09-25 16:26:31 +02:00
Robert Sachunsky	ef1304a764	CLIs: reorder options, explain -i vs -di	2025-09-25 16:11:39 +02:00
Robert Sachunsky	df5448cdcd	CLIs: add required=True where missing	2025-09-25 16:08:40 +02:00
b-vr103	369ef573f9	get textlines sorted in textregions - detection of vertical and horizontal regions improved	2025-09-25 12:51:02 +02:00
Robert Sachunsky	9967510327	mbreorder: filter by .xml suffix in dir-in mode	2025-09-25 01:15:37 +02:00
Robert Sachunsky	b094a6b77f	mbreorder: avoid spaces in logger name	2025-09-25 01:15:37 +02:00
Robert Sachunsky	d6cdb69acb	binarize/enhance/layout/ocr ls_imgs: use the same file name suffix filter for dir-in mode	2025-09-25 01:15:37 +02:00
Robert Sachunsky	96a0d22496	mbreorder CLI: change options to mimic other commands	2025-09-25 01:15:37 +02:00
Robert Sachunsky	93f7588bfa	binarizer CLI: add --log-level	2025-09-24 23:08:50 +02:00
Robert Sachunsky	8a1e5a8950	enhancement / layout CLI: do not override logger name	2025-09-24 23:03:11 +02:00
Robert Sachunsky	960b11f51f	machine-based-reading-order CLI: no foreign logger, add --log-level	2025-09-24 22:58:57 +02:00
kba	45b05c2316	Merge branch 'mbro_dead_code' into prepare-release-v0.5.0	2025-09-24 17:18:31 +02:00
vahidrezanezhad	80d50d4bf6	get textlines sorted in textregion - verticals	2025-09-24 17:17:27 +02:00
b-vr103	6d8641a518	get textlines sorted in textregion - verticals	2025-09-24 17:17:21 +02:00
vahidrezanezhad	6904a98182	get textlines inside textregion sorted debugging	2025-09-24 17:17:12 +02:00
vahidrezanezhad	ce13d8c5a3	get textlines inside textregion sorted	2025-09-24 17:16:47 +02:00
kba	8b30bdbae2	image_enhancer: use latest page extraction model	2025-09-24 16:39:31 +02:00
kba	c8ebe84697	image_enhancer: add missing models, remove dead code	2025-09-24 16:36:18 +02:00
kba	b75ca0d31f	mb_ro_on_layout: remove copy-pasta code not actually used	2025-09-24 16:29:05 +02:00
Robert Sachunsky	5bd318e657	rm print statement (already log msg)	2025-09-24 12:14:32 +02:00
Robert Sachunsky	90f1d7aa47	rm summary msg (info already logged elsewhere)	2025-09-24 12:10:11 +02:00
Robert Sachunsky	7933b103f5	log modes only once (in run, not in run_single)	2025-09-24 12:09:30 +02:00
Robert Sachunsky	d0817f5744	fix typo	2025-09-24 12:08:50 +02:00
kba	9ead58b99a	Merge remote-tracking branch 'michalbubula/add-feedback' into prepare-release-v0.5.0	2025-09-23 19:50:27 +02:00
kba	7bde99e866	Merge remote-tracking branch 'origin/updating_readme_for_eynollah_use_cases' into prepare-release-v0.5.0	2025-09-23 19:42:55 +02:00
kba	df8d93dbfa	Merge branch 'main' into add-feedback	2025-09-23 19:20:20 +02:00