2010-09-30 07:14:42 +08:00
|
|
|
UNICHARSET_EXTRACTOR(1)
|
|
|
|
|
=======================
|
|
|
|
|
|
|
|
|
|
NAME
|
|
|
|
|
----
|
2019-05-31 16:20:19 +08:00
|
|
|
unicharset_extractor - Reads box or plain text files to extract the unicharset.
|
2010-09-30 07:14:42 +08:00
|
|
|
|
|
|
|
|
SYNOPSIS
|
|
|
|
|
--------
|
2019-05-31 16:20:19 +08:00
|
|
|
*unicharset_extractor* [--output_unicharset filename] [--norm_mode mode] box_or_text_file [...]
|
|
|
|
|
|
|
|
|
|
Where mode means:
|
|
|
|
|
1=combine graphemes (use for Latin and other simple scripts)
|
|
|
|
|
2=split graphemes (use for Indic/Khmer/Myanmar)
|
|
|
|
|
3=pure unicode (use for Arabic/Hebrew/Thai/Tibetan)
|
2010-09-30 07:14:42 +08:00
|
|
|
|
|
|
|
|
DESCRIPTION
|
|
|
|
|
-----------
|
2016-12-05 03:41:37 +08:00
|
|
|
Tesseract needs to know the set of possible characters it can output.
|
|
|
|
|
To generate the unicharset data file, use the unicharset_extractor
|
2019-05-31 16:20:19 +08:00
|
|
|
program on training pages bounding box files or a plain text file:
|
2010-09-30 07:14:42 +08:00
|
|
|
|
|
|
|
|
unicharset_extractor fontfile_1.box fontfile_2.box ...
|
|
|
|
|
|
2019-05-31 16:20:19 +08:00
|
|
|
The unicharset will be put into the file './unicharset' if no output filename is provided.
|
2010-09-30 07:14:42 +08:00
|
|
|
|
2019-05-31 16:20:19 +08:00
|
|
|
*NOTE* Use the appropriate norm_mode based on the language.
|
2010-09-30 07:14:42 +08:00
|
|
|
|
|
|
|
|
SEE ALSO
|
|
|
|
|
--------
|
|
|
|
|
tesseract(1), unicharset(5)
|
|
|
|
|
|
2015-06-13 06:08:05 +08:00
|
|
|
<https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract>
|
2012-02-10 06:55:47 +08:00
|
|
|
|
2010-09-30 07:14:42 +08:00
|
|
|
HISTORY
|
|
|
|
|
-------
|
|
|
|
|
unicharset_extractor first appeared in Tesseract 2.00.
|
|
|
|
|
|
|
|
|
|
COPYING
|
|
|
|
|
-------
|
2012-02-10 06:55:47 +08:00
|
|
|
Copyright \(C) 2006, Google Inc.
|
2010-09-30 07:14:42 +08:00
|
|
|
Licensed under the Apache License, Version 2.0
|
2012-02-10 06:55:47 +08:00
|
|
|
|
|
|
|
|
AUTHOR
|
|
|
|
|
------
|
|
|
|
|
The Tesseract OCR engine was written by Ray Smith and his research groups
|
|
|
|
|
at Hewlett Packard (1985-1995) and Google (2006-present).
|
