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

# shapeclustering(1)

shape clustering training for Tesseract

## NAME

shapeclustering - shape clustering training for Tesseract

## SYNOPSIS

shapeclustering -D *output\_dir* -U *unicharset* -O *mfunicharset* -F *font\_props* -X *xheights* *FILE*...

## DESCRIPTION

[shapeclustering(1)](/shapeclustering/1.md) takes extracted feature .tr files (generated by [tesseract(1)](/tesseract/1.md) run in a special mode from box files) and produces a file **shapetable** and an enhanced unicharset. This program is still experimental, and is not required (yet) for training Tesseract.

## OPTIONS

- \-U *FILE*

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

- \-D *dir*

  Directory to write output files to.

- \-F *font\_properties\_file*

  (Input) font properties file, where 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'
  ```

- \-O *FILE*

  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), [unicharset(5)](/unicharset/5.md)

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

## COPYING

Copyright (C) Google, 2011 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).