1MFTRAINING(1)                                                    MFTRAINING(1)
2
3
4

NAME

6       mftraining - feature training for Tesseract
7

SYNOPSIS

9       mftraining -U unicharset -O lang.unicharset FILE...
10

DESCRIPTION

12       mftraining takes a list of .tr files, from which it generates the files
13       inttemp (the shape prototypes), shapetable, and pffmtable (the number
14       of expected features for each character). (A fourth file called
15       Microfeat is also written by this program, but it is not used.)
16

OPTIONS

18       -U FILE
19           (Input) The unicharset generated by unicharset_extractor(1)
20
21       -F font_properties_file
22           (Input) font properties file, each line is of the following form,
23           where each field other than the font name is 0 or 1:
24
25               *font_name* *italic* *bold* *fixed_pitch* *serif* *fraktur*
26
27       -X xheights_file
28           (Input) x heights file, each line is of the following form, where
29           xheight is calculated as the pixel x height of a character drawn at
30           32pt on 300 dpi. [ That is, if base x height + ascenders +
31           descenders = 133, how much is x height? ]
32
33               *font_name* *xheight*
34
35       -D dir
36           Directory to write output files to.
37
38       -O FILE
39           (Output) The output unicharset that will be given to
40           combine_tessdata(1)
41

SEE ALSO

43       tesseract(1), cntraining(1), unicharset_extractor(1),
44       combine_tessdata(1), shapeclustering(1), unicharset(5)
45
46       https://tesseract-ocr.github.io/tessdoc/Training-Tesseract.html
47

COPYING

49       Copyright (C) Hewlett-Packard Company, 1988 Licensed under the Apache
50       License, Version 2.0
51

AUTHOR

53       The Tesseract OCR engine was written by Ray Smith and his research
54       groups at Hewlett Packard (1985-1995) and Google (2006-present).
55
56
57
58                                  07/22/2023                     MFTRAINING(1)