mftraining(1) [debian man page]

MFTRAINING(1)															     MFTRAINING(1)

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)

       -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)

SEE ALSO

       tesseract(1), cntraining(1), unicharset_extractor(1), combine_tessdata(1), shapeclustering(1), unicharset(5)

       http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3

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-present).

								    02/09/2012							     MFTRAINING(1)

ADDFTINFO(1)						      General Commands Manual						      ADDFTINFO(1)

NAME

       addftinfo - add information to troff font files for use with groff

SYNOPSIS

       addftinfo [ -v ] [ -param value...  ] res unitwidth font

DESCRIPTION

       addftinfo  reads  a  troff font file and adds some additional font-metric information that is used by the groff system.	The font file with
       the information added is written on the standard output.  The information added is guessed using some parametric information about the font
       and assumptions about the traditional troff names for characters.  The main information added is the heights and depths of characters.  The
       res and unitwidth arguments should be the same as the corresponding parameters in the DESC file; font is the name of  the  file	describing
       the font; if font ends with I the font will be assumed to be italic.

OPTIONS

       -v prints the version number.

       All  other  options  changes one of the parameters that is used to derive the heights and depths.  Like the existing quantities in the font
       file, each value is in inches/res for a font whose point size is unitwidth.  param must be one of:

       x-height
	      The height of lowercase letters without ascenders such as x.

       fig-height
	      The height of figures (digits).

       asc-height
	      The height of characters with ascenders, such as b, d or l.

       body-height
	      The height of characters such as parentheses.

       cap-height
	      The height of uppercase letters such as A.

       comma-depth
	      The depth of a comma.

       desc-depth
	      The depth of characters with descenders, such as p,q, or y.

       body-depth
	      The depth of characters such as parentheses.

       addftinfo makes no attempt to use the specified parameters to guess the unspecified parameters.	 If  a	parameter  is  not  specified  the
       default will be used.  The defaults are chosen to have the reasonable values for a Times font.

SEE ALSO

       groff_font(5), groff(1), groff_char(7)

Groff Version 1.21						 31 December 2010						      ADDFTINFO(1)