1UNICHARSET_EXTRACTOR(1) UNICHARSET_EXTRACTOR(1)
2
3
4
6 unicharset_extractor - extract unicharset from Tesseract boxfiles
7
9 unicharset_extractor [-D dir] FILE...
10
12 Tesseract needs to know the set of possible characters it can output.
13 To generate the unicharset data file, use the unicharset_extractor
14 program on the same training pages bounding box files as used for
15 clustering:
16
17 unicharset_extractor fontfile_1.box fontfile_2.box ...
18
19 The unicharset will be put into the file dir/unicharset, or simply
20 ./unicharset if no output directory is provided.
21
22 Tesseract also needs to have access to character properties isalpha,
23 isdigit, isupper, islower, ispunctuation. all of this auxilury data and
24 more is encoded in this file. (See unicharset(5))
25
26 If your system supports the wctype functions, these values will be set
27 automatically by unicharset_extractor and there is no need to edit the
28 unicharset file. On some older systems (eg Windows 95), the unicharset
29 file must be edited by hand to add these property description codes.
30
31 NOTE The unicharset file must be regenerated whenever inttemp,
32 normproto and pffmtable are generated (i.e. they must all be recreated
33 when the box file is changed) as they have to be in sync. This is made
34 easier than in previous versions by running unicharset_extractor before
35 mftraining and cntraining, and giving the unicharset to mftraining.
36
38 tesseract(1), unicharset(5)
39
40 https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract
41
43 unicharset_extractor first appeared in Tesseract 2.00.
44
46 Copyright (C) 2006, Google Inc. Licensed under the Apache License,
47 Version 2.0
48
50 The Tesseract OCR engine was written by Ray Smith and his research
51 groups at Hewlett Packard (1985-1995) and Google (2006-present).
52
53
54
55 06/12/2015 UNICHARSET_EXTRACTOR(1)