---
name: "mftraining"
section: "1"
platform: "linux"
package: "tesseract-ocr"
version: "5.5.0-1+b1"
release: "Debian 13 (Trixie)"
platforms: ["linux"]
url: "https://new.carta.tech/mftraining"
---

# mftraining(1)

feature training for Tesseract

## NAME

mftraining - feature training for Tesseract

## SYNOPSIS

mftraining -U *unicharset* -O *lang.unicharset* *FILE*...

## DESCRIPTION

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

## OPTIONS

- \-U *FILE*

  (Input) The unicharset generated by [unicharset\_extractor(1)](/unicharset_extractor/1.md)

- \-F *font\_properties\_file*

  (Input) font properties file, each line is of the following form, where each field other than the font name is 0 or 1:

  ```
  *font_name* *italic* *bold* *fixed_pitch* *serif* *fraktur*
  ```

- \-X *xheights\_file*

  (Input) x heights file, each line is of the following form, where xheight is calculated as the pixel x height of a character drawn at 32pt on 300 dpi. \[ That is, if base x height + ascenders + descenders = 133, how much is x height? \]

  ```
  *font_name* *xheight*
  ```

- \-D *dir*

  Directory to write output files to.

- \-O *FILE*

  (Output) The output unicharset that will be given to [combine\_tessdata(1)](/combine_tessdata/1.md)

## SEE ALSO

[tesseract(1)](/tesseract/1.md), [cntraining(1)](/cntraining/1.md), [unicharset\_extractor(1)](/unicharset_extractor/1.md), [combine\_tessdata(1)](/combine_tessdata/1.md), [shapeclustering(1)](/shapeclustering/1.md), [unicharset(5)](/unicharset/5.md)

**https://tesseract-ocr.github.io/tessdoc/Training-Tesseract.html**

## COPYING

Copyright (C) Hewlett-Packard Company, 1988 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 (2006-2018).