1UNICHARSET_EXTRACTOR(1)                                UNICHARSET_EXTRACTOR(1)
2
3
4

NAME

6       unicharset_extractor - Reads box or plain text files to extract the
7       unicharset.
8

SYNOPSIS

10       unicharset_extractor [--output_unicharset filename] [--norm_mode mode]
11       box_or_text_file [...]
12
13       Where mode means: 1=combine graphemes (use for Latin and other simple
14       scripts) 2=split graphemes (use for Indic/Khmer/Myanmar) 3=pure unicode
15       (use for Arabic/Hebrew/Thai/Tibetan)
16

DESCRIPTION

18       Tesseract needs to know the set of possible characters it can output.
19       To generate the unicharset data file, use the unicharset_extractor
20       program on training pages bounding box files or a plain text file:
21
22           unicharset_extractor fontfile_1.box fontfile_2.box ...
23
24       The unicharset will be put into the file ./unicharset if no output
25       filename is provided.
26
27       NOTE Use the appropriate norm_mode based on the language.
28

SEE ALSO

30       tesseract(1), unicharset(5)
31
32       https://tesseract-ocr.github.io/tessdoc/Training-Tesseract.html
33

HISTORY

35       unicharset_extractor first appeared in Tesseract 2.00.
36

COPYING

38       Copyright (C) 2006, Google Inc. Licensed under the Apache License,
39       Version 2.0
40

AUTHOR

42       The Tesseract OCR engine was written by Ray Smith and his research
43       groups at Hewlett Packard (1985-1995) and Google (2006-present).
44
45
46
47                                  02/25/2022           UNICHARSET_EXTRACTOR(1)