Commit Graph

54 Commits (2bd4ae8d5a7a7b5c1ac9d26099f2af56edf67919)
 

Author SHA1 Message Date
Kai 2bd4ae8d5a add ned-priority option to page2tsv
Kai d4eb95b64b make code more robust
Kai 49861b1652 support confidences in find-entities
Kai 0da38d6ec6 support confidences in find-entities
Kai 9b3198e401 add priority option for find-entities
Kai 7b53cc5539 add priority option for find-entities
Kai 318d9bd122 fix
Kai Labusch abcdb67e9e
Merge pull request from kba/lineid-ocr-tsv
Retain line_id, tsv2page CLI to propagate results back to PAGE-XML
Konstantin Baierer f03acbf54d tsv2page CLI to propagate TSV results back to PAGE-XML
Konstantin Baierer ad379aea2b store pc:TextLine ID in TSV, fix
Kai Labusch 9c63631d7a
Merge pull request from kba/core-page-api
use OCR-D/core PAGE API for reading order and recursive regions
Konstantin Baierer 675c88a67d requirements: ocrd pulls in requests already
Konstantin Baierer d80b02c56d use OCR-D/core PAGE API for reading order and recursive regions
Kai Labusch e21fbc09a1 fix url
Kai 1ec06a3087 fix setup.py
Kai Labusch eca7823b10
Merge pull request from qurator-spk/cneud-patch-1
fix snippets
Clemens Neudecker 5c82b83b2e
fix snippets
use `full` resolution IIIF image for snippets
Kai 243c7b48c6 fix line shift
Kai 6ffba183ab fix repeated text lines
Kai de575037e6 fix repeated text rows
Kai a6008b83b5 remove full
Kai 487b74b6e6
Kai c554644838 Add directory parsing option to make-page2tsv-commands
Kai aa79678403 Add directory parsing option to make-page2tsv-commands
Kai 7fc39739b7 Add directory parsing option to make-page2tsv-commands
Kai f606cb92b0 Change scale-factor default parameter. Fix make-page2tsv-commands
Kai 900015da61 store OCR or NED confidences in tsv file
Kai 5d55ba24a3 use max confidence instead of mean
Kai 85ec36218e support visualization of ocr confidences
Kai 2b73b421ae support visualization of ocr confidences
Kai c3acd74e9f add OCR annotation functionality
Kai Labusch a834da494a permit empty files
Kai Labusch 2dc3857770 make tools more robust against glitches within the input files
Kai Labusch e09f40db61 proper support for retroactive entity linking
U-PK\b-kl104 449bd1d3ca preserve URL structure in tsv files during NER/NED amendment
Kai Labusch 361c811264 add command line tool that creates page2tsv commands from an excel file
Kai 83fb2ea033 enable NED only usage of find-entities
Kai c12bea2cb0 enable NED only usage of find-entities
Kai Labusch 975487a233 adapt find-entities to CLEF2020 requirements
Kai 0d650ebcc5 support loading ned result from disk
Kai 9fe35377e3 disable proxy option in find-entities
Kai c7f4b6fe53 add proper NED support
Kai 24fd7245f5 add findentities command line tool that can be used in order to NER/NED tag an existing .tsv file
Kai b13dae29f5 rename GND-ID column to more generic ID
Kai Labusch 0cd9cd932a support automatic named entity disambiguation
Kai Labusch 05f49df6d2 support Qurator calamari PAGE xml
Kai Labusch abdabbac4f try to infer correct line ordering ...
Kai Labusch 7bf9cfa5de try to infer correct line ordering ...
Clemens Neudecker e535a070c4
Update cli.py
Kai Labusch 2946909cf3 add command line option for image scale factor