2018-03-13 02:08:16 +08:00
|
|
|
MERGE_UNICHARSETS(1)
|
|
|
|
|
====================
|
|
|
|
|
:doctype: manpage
|
|
|
|
|
|
|
|
|
|
NAME
|
|
|
|
|
----
|
|
|
|
|
merge_unicharsets - Simple tool to merge two or more unicharsets.
|
|
|
|
|
|
|
|
|
|
SYNOPSIS
|
|
|
|
|
--------
|
|
|
|
|
*merge_unicharsets* 'unicharset-in-1' ... 'unicharset-in-n' 'unicharset-out'
|
|
|
|
|
|
|
|
|
|
DESCRIPTION
|
|
|
|
|
-----------
|
|
|
|
|
merge_unicharsets(1) is a simple tool to merge two or more unicharsets.
|
2017-09-17 00:47:04 +08:00
|
|
|
It could be used to create a combined unicharset for a script-level engine,
|
2018-03-13 02:08:16 +08:00
|
|
|
like the new Latin or Devanagari.
|
|
|
|
|
|
|
|
|
|
IN/OUT ARGUMENTS
|
|
|
|
|
----------------
|
|
|
|
|
'unicharset-in-1'::
|
|
|
|
|
(Input) The name of the first unicharset file to be merged.
|
2017-09-17 00:47:04 +08:00
|
|
|
|
2018-03-13 02:08:16 +08:00
|
|
|
'unicharset-in-n'::
|
|
|
|
|
(Input) The name of the nth unicharset file to be merged.
|
|
|
|
|
|
|
|
|
|
'unicharset-out'::
|
|
|
|
|
(Output) The name of the merged unicharset file.
|
2017-09-17 00:47:04 +08:00
|
|
|
|
2018-03-13 02:08:16 +08:00
|
|
|
HISTORY
|
|
|
|
|
-------
|
2017-09-17 00:47:04 +08:00
|
|
|
merge_unicharsets(1) was first made available for tesseract4.00.00alpha.
|
2018-03-13 02:08:16 +08:00
|
|
|
|
|
|
|
|
RESOURCES
|
|
|
|
|
---------
|
|
|
|
|
Main web site: <https://github.com/tesseract-ocr> +
|
|
|
|
|
Information on training tesseract LSTM: <https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00>
|
|
|
|
|
|
|
|
|
|
SEE ALSO
|
|
|
|
|
--------
|
|
|
|
|
tesseract(1)
|
|
|
|
|
|
|
|
|
|
COPYING
|
|
|
|
|
-------
|
|
|
|
|
Copyright \(C) 2012 Google, Inc.
|
|
|
|
|
Licensed under the Apache License, Version 2.0
|
|
|
|
|
|
|
|
|
|
AUTHOR
|
|
|
|
|
------
|
|
|
|
|
The Tesseract OCR engine was written by Ray Smith and his research groups
|
|
|
|
|
at Hewlett Packard (1985-1995) and Google (2006-present).
|
