mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-24 02:59:07 +08:00
577e8a8b93
Add PAGE XML export and documentation. To generate PAGE XML output just add 'page' to the tesseract command. The output is outputname + '.page.xml' to avoid conflicts with ALTO export. The output can be customized with the flags: tessedit_create_page_polygon and tessedit_create_page_wordlevel. Co-authored-by: Stefan Weil <sw@weilnetz.de>
9 lines
370 B
Makefile
9 lines
370 B
Makefile
datadir = @datadir@/tessdata/configs
|
|
data_DATA = inter makebox box.train unlv ambigs.train lstm.train lstmdebug
|
|
data_DATA += api_config kannada box.train.stderr quiet logfile digits get.images
|
|
data_DATA += lstmbox wordstrbox
|
|
# Configurations for OCR output.
|
|
data_DATA += alto hocr page pdf tsv txt
|
|
data_DATA += linebox rebox strokewidth bigram
|
|
EXTRA_DIST = $(data_DATA)
|