45 commits

Author	SHA1	Message	Date
Konstantin Baierer	abeca0df16	drop requirement for matplotlib (not used)	2022-10-24 14:29:42 +02:00
Konstantin Baierer	db25239075	Merge branch 'master' into ocrd-processors ... # Conflicts: # setup.py	2022-10-24 14:02:24 +02:00
Kai	75796b5c0c	refactor	2022-06-10 10:00:32 +02:00
Konstantin Baierer	60a07c6310	drop support for scaling, not necessary for SBB use case anymore	2022-05-30 16:58:20 +02:00
Konstantin Baierer	aabcc4866d	remove obsolete tsv.py (now in qurator-sbb-tools	2022-02-21 18:50:09 +01:00
Konstantin Baierer	f813c45ba2	Merge remote-tracking branch 'origin/master' into ocrd-processors	2022-02-21 18:47:10 +01:00
Konstantin Baierer	aeb67e445f	implement page2tsv/tsv2page as ocrd-neat-{ex,im}port	2022-02-21 18:47:03 +01:00
Konstantin Baierer	0aee20a7f6	cli: separate tsv2page and tsv2page_cli	2022-02-21 17:04:54 +01:00
Konstantin Baierer	fe0c355e5a	cli: produce TSV if no words are transcribed	2022-02-21 17:00:03 +01:00
Konstantin Baierer	93ee53c8e2	cli: split page2tsv from page2tsv_cli	2022-02-21 15:22:04 +01:00
Kai	9d2d5fcd31	add missing imports	2022-02-21 14:03:07 +01:00
Kai	568e1cd104	remove ner/ned code from page2tsv package	2021-12-15 15:51:00 +01:00
Kai	ed90193c45	support segmentation only Page-XML	2021-11-19 11:27:46 +01:00
Kai	ee5f03ce07	change default scale factor to 1.0	2021-05-07 12:36:42 +02:00
Kai	5e60fabe4a	revert changes	2021-05-07 11:28:24 +02:00
Kai	e5b635ec2d	try other coordinate computation	2021-05-07 10:50:09 +02:00
Kai	f320904503	try other coordinate computation	2021-05-07 10:40:52 +02:00
Kai	1eb05d0d62	xlrd does not support xsls files anymore	2021-05-07 08:02:33 +02:00
Kai	ae93668bac	xlrd does not support xsls files anymore	2021-05-07 07:54:55 +02:00
Kai	2bd4ae8d5a	add ned-priority option to page2tsv	2021-05-06 16:23:08 +02:00
Kai	d4eb95b64b	make code more robust	2021-05-06 15:13:26 +02:00
Kai	49861b1652	support confidences in find-entities	2021-05-06 13:17:07 +02:00
Kai	0da38d6ec6	support confidences in find-entities	2021-05-06 13:01:41 +02:00
Kai	9b3198e401	add priority option for find-entities	2021-05-06 12:42:12 +02:00
Kai	7b53cc5539	add priority option for find-entities	2021-05-06 12:24:47 +02:00
Kai	318d9bd122	fix #7	2021-04-09 08:07:27 +02:00
Konstantin Baierer	f03acbf54d	tsv2page CLI to propagate TSV results back to PAGE-XML	2021-04-01 17:53:27 +02:00
Konstantin Baierer	ad379aea2b	store pc:TextLine ID in TSV, fix #5	2021-04-01 17:13:30 +02:00
Konstantin Baierer	d80b02c56d	use OCR-D/core PAGE API for reading order and recursive regions	2021-04-01 15:21:03 +02:00
Kai Labusch	e21fbc09a1	fix url	2021-03-18 21:20:46 +01:00
Clemens Neudecker	5c82b83b2e	fix snippets ... use `full` resolution IIIF image for snippets	2021-03-10 16:59:09 +01:00
Kai	243c7b48c6	fix line shift	2021-03-10 16:08:39 +01:00
Kai	6ffba183ab	fix repeated text lines	2021-03-10 15:33:30 +01:00
Kai	de575037e6	fix repeated text rows	2021-03-10 15:15:24 +01:00
Kai	a6008b83b5	remove full	2021-03-10 15:11:38 +01:00
Kai	487b74b6e6	#2	2021-03-10 14:06:51 +01:00
Kai	c554644838	Add directory parsing option to make-page2tsv-commands	2021-03-10 12:03:45 +01:00
Kai	aa79678403	Add directory parsing option to make-page2tsv-commands	2021-03-10 11:57:39 +01:00
Kai	7fc39739b7	Add directory parsing option to make-page2tsv-commands	2021-03-10 11:51:49 +01:00
Kai	f606cb92b0	Change scale-factor default parameter. Fix make-page2tsv-commands	2021-03-10 11:15:42 +01:00
Kai	900015da61	store OCR or NED confidences in tsv file	2021-02-26 12:18:10 +01:00
Kai	5d55ba24a3	use max confidence instead of mean	2021-02-04 07:37:58 +01:00
Kai	85ec36218e	support visualization of ocr confidences	2021-02-03 15:31:36 +01:00
Kai	2b73b421ae	support visualization of ocr confidences	2021-02-03 15:22:38 +01:00
Kai	c3acd74e9f	add OCR annotation functionality	2021-02-01 16:25:12 +01:00