2010-09-30 00:29:49 +08:00
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook XML V4.5//EN" "http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd">
2010-09-30 00:46:04 +08:00
<?asciidoc-toc?>
<?asciidoc-numbered?>
2010-09-30 00:29:49 +08:00
<refentry lang= "en" >
<refmeta >
<refentrytitle > tesseract</refentrytitle>
<manvolnum > 1</manvolnum>
2010-09-30 00:46:04 +08:00
<refmiscinfo class= "source" > </refmiscinfo>
<refmiscinfo class= "manual" > </refmiscinfo>
2010-09-30 00:29:49 +08:00
</refmeta>
<refnamediv >
<refname > tesseract</refname>
<refpurpose > command-line OCR engine</refpurpose>
</refnamediv>
2010-09-30 00:46:04 +08:00
<refsynopsisdiv id= "_synopsis" >
2010-09-30 00:29:49 +08:00
<simpara > <emphasis role= "strong" > tesseract</emphasis> <emphasis > imagename</emphasis> <emphasis > textbase</emphasis> [<emphasis > configfile</emphasis> ] [<emphasis > -l lang</emphasis> ]</simpara>
</refsynopsisdiv>
2010-09-30 00:46:04 +08:00
<refsect1 id= "_description" >
2010-09-30 00:29:49 +08:00
<title > DESCRIPTION</title>
<simpara > tesseract(1) is a commercial quality OCR engine originally developed at HP
between 1985 and 1995. In 1995, this engine was among the top 3 evaluated by
UNLV. It was open-sourced by HP and UNLV in 2005, and has been developed
by Google since then.</simpara>
</refsect1>
2010-09-30 00:46:04 +08:00
<refsect1 id= "_options" >
2010-09-30 00:29:49 +08:00
<title > OPTIONS</title>
<simpara > <emphasis > imagename</emphasis>
2010-09-30 00:46:04 +08:00
The name of the input image</simpara>
2010-09-30 00:29:49 +08:00
<simpara > <emphasis > textbase</emphasis>
2010-09-30 00:46:04 +08:00
The basename of the output file (to which the appropriate extension
will be appended)</simpara>
2010-09-30 00:29:49 +08:00
<simpara > <emphasis > configfile</emphasis>
2010-09-30 00:46:04 +08:00
The config to use. A config is a plaintext file which contains a list
of variables and their values, one per line, with a space separating
variable from value.</simpara>
2010-09-30 00:29:49 +08:00
<simpara > <emphasis > -l lang</emphasis>
2010-09-30 00:46:04 +08:00
The language to use. If none is specified, English is assumed.
Tesseract uses 3-character ISO 639-2 language codes. (See LANGUAGES)</simpara>
2010-09-30 00:29:49 +08:00
<simpara > <emphasis > -v</emphasis>
2010-09-30 00:46:04 +08:00
Returns the current version of the tesseract(1) executable.</simpara>
2010-09-30 00:29:49 +08:00
</refsect1>
2010-09-30 00:46:04 +08:00
<refsect1 id= "_languages" >
2010-09-30 00:29:49 +08:00
<title > LANGUAGES</title>
<simpara > There are currently language packs available for the following languages:</simpara>
2010-09-30 01:59:10 +08:00
<informaltable tabstyle= "horizontal" frame= "none" colsep= "0" rowsep= "0" > <tgroup cols= "2" > <colspec colwidth= "15*" /> <colspec colwidth= "85*" /> <tbody valign= "top" >
<row >
<entry >
<simpara >
bul
</simpara>
</entry>
<entry >
<simpara >
Bulgarian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
cat
</simpara>
</entry>
<entry >
<simpara >
Catalan
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
ces
</simpara>
</entry>
<entry >
<simpara >
Czech
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
chi_sim
</simpara>
</entry>
<entry >
<simpara >
Simplified Chinese
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
chi_tra
</simpara>
</entry>
<entry >
<simpara >
Traditional Chinese
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
dan
</simpara>
</entry>
<entry >
<simpara >
Danish
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
dan-frak
</simpara>
</entry>
<entry >
<simpara >
Danish (Fraktur)
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
deu
</simpara>
</entry>
<entry >
<simpara >
German
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
ell
</simpara>
</entry>
<entry >
<simpara >
Greek
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
eng
</simpara>
</entry>
<entry >
<simpara >
English
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
fin
</simpara>
</entry>
<entry >
<simpara >
Finnish
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
fra
</simpara>
</entry>
<entry >
<simpara >
French
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
hun
</simpara>
</entry>
<entry >
<simpara >
Hungarian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
ind
</simpara>
</entry>
<entry >
<simpara >
Indonesian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
ita
</simpara>
</entry>
<entry >
<simpara >
Italian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
jpn
</simpara>
</entry>
<entry >
<simpara >
Japanese
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
kor
</simpara>
</entry>
<entry >
<simpara >
Korean
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
lav
</simpara>
</entry>
<entry >
<simpara >
Latvian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
lit
</simpara>
</entry>
<entry >
<simpara >
Lithuanian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
nld
</simpara>
</entry>
<entry >
<simpara >
Dutch
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
nor
</simpara>
</entry>
<entry >
<simpara >
Norwegian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
pol
</simpara>
</entry>
<entry >
<simpara >
Polish
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
por
</simpara>
</entry>
<entry >
<simpara >
Portuguese
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
ron
</simpara>
</entry>
<entry >
<simpara >
Romanian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
rus
</simpara>
</entry>
<entry >
<simpara >
Russian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
slk
</simpara>
</entry>
<entry >
<simpara >
Slovakian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
slv
</simpara>
</entry>
<entry >
<simpara >
Slovenian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
spa
</simpara>
</entry>
<entry >
<simpara >
Spanish
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
srp
</simpara>
</entry>
<entry >
<simpara >
Serbian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
swe
</simpara>
</entry>
<entry >
<simpara >
Swedish
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
tgl
</simpara>
</entry>
<entry >
<simpara >
Tagalog
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
tha
</simpara>
</entry>
<entry >
<simpara >
Thai
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
tur
</simpara>
</entry>
<entry >
<simpara >
Turkish
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
ukr
</simpara>
</entry>
<entry >
<simpara >
Ukrainian
</simpara>
</entry>
</row>
<row >
<entry >
<simpara >
vie
</simpara>
</entry>
<entry >
<simpara >
Vietnamese
</simpara>
</entry>
</row>
</tbody> </tgroup> </informaltable>
2010-09-30 00:29:49 +08:00
</refsect1>
2010-09-30 00:46:04 +08:00
<refsect1 id= "_history" >
2010-09-30 00:29:49 +08:00
<title > HISTORY</title>
2010-09-30 00:46:04 +08:00
<simpara > The engine was developed at Hewlett Packard Laboratories Bristol and at
Hewlett Packard Co, Greeley Colorado between 1985 and 1994, with some more
changes made in 1996 to port to Windows, and some C++izing in 1998. A
lot of the code was written in C, and then some more was written in C++.
Since then all the code has been converted to at least compile with a
2010-09-30 01:56:39 +08:00
C++ compiler. Currently it builds under Linux with gcc4.0, gcc4.1 and
under Windows with VC++6 and VC++Express. The C++ code makes heavy use of
2010-09-30 00:46:04 +08:00
a list system using macros. This predates stl, was portable before stl, and
is more efficient than stl lists, but has the big negative that if you do get
a segmentation violation, it is hard to debug. Another "feature" of the
2010-09-30 01:56:39 +08:00
C/C++ split is that the C++ data structures get converted to C data
structures to call the low-level C code. This is ugly, and the C++izing of
2010-09-30 00:46:04 +08:00
the C code is a step towards eliminating the conversion, but it has not
happened yet.</simpara>
<simpara > The most important changes in version 2.00 were that Tesseract can now
recognize 6 languages, is fully UTF8 capable, and is fully trainable. See
<ulink url= "http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract" > http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract</ulink> for more
information on training.</simpara>
<simpara > Tesseract was included in UNLV’ s Fourth Annual Test of OCR Accuracy.
See <ulink url= "http://www.isri.unlv.edu/downloads/AT-1995.pdf" > http://www.isri.unlv.edu/downloads/AT-1995.pdf</ulink> . With Tesseract 2.00,
scripts are now included to allow anyone to reproduce some of these tests.
See <ulink url= "http://code.google.com/p/tesseract-ocr/wiki/TestingTesseract" > http://code.google.com/p/tesseract-ocr/wiki/TestingTesseract</ulink> for more
details.</simpara>
<simpara > Tesseract 3.00 adds a number of new languages, including Chinese, Japanese,
and Korean. It also introduces a new, single-file based system of managing
language data. For further details, see the file ReleaseNotes included with
the distribution.</simpara>
2010-09-30 00:29:49 +08:00
</refsect1>
2010-09-30 00:46:04 +08:00
<refsect1 id= "_see_also" >
2010-09-30 00:29:49 +08:00
<title > SEE ALSO</title>
<simpara > tesseract(1)</simpara>
</refsect1>
2010-09-30 00:46:04 +08:00
<refsect1 id= "_copying" >
2010-09-30 00:29:49 +08:00
<title > COPYING</title>
<simpara > Licensed under the Apache License, Version 2.0</simpara>
</refsect1>
</refentry>