View source for Optical character recognition with Tesseract



==install==
Tesseract (with languages you will be using) 
* Mac <code>brew install tesseract --all-languages</code>
* Debian/Ubuntu: <code>sudo aptitude install tesseract-ocr</code> 
** See what language packages are available with: <code>sudo aptitude search tesseract-ocr-</code>
** install language packages: <code>sudo aptitude install tesseract-ocr-ara tesseract-ocr-port tesseract-ocr-spa</code> here I am installing Arabic, Portuguese, Spanish

poppler-utils whic include tools such as pdftotext and pdftohtml
* Mac <code>brew install poppler-utils</code>
* Debian/Ubuntu: <code>sudo aptitude install poppler-utils</code> 

imagemagick 
* Mac <code>brew install imagemagick</code>
* Debian/Ubuntu: <code>sudo aptitude install imagemagick</code> 

pdftk
* Mac <code>brew install pdftk</code>
* Debian/Ubuntu: <code>sudo aptitude install pdftk</code> 


=PDF=
* with text layer
* without text layer
To find out the difference you can try to select the PDF's text in a PDF viewer. Only if the text layer is present will you be able to select it.

If it contains a text layer you can use pdftotext command-line application (from poppler-utils) to convert the PDF to text 


= Tesseract=
<blockquote>Tesseract was originally 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. In 2005 Tesseract was open sourced by HP. Since 2006 it is developed by Google.<ref>https://github.com/tesseract-ocr/tesseract/blob/master/README.md</ref></blockquote>

[https://code.google.com/p/tesseract-ocr/ Tesseract] is a Free software OCR package


==one page prototype==
Getting 1 page from PDF file with PDFTK <code>burst</code>

 pdftk yourfile.pdf burst 

Chose page you want to convert 

Convert PDF to bit-map using imagemagick, with some options to optimize OCR
 convert -density 300 page.pdf -depth 8 -strip -background white -alpha off ouput.tiff
* <code>-density 300</code> resolution 300DPI. Lower resolutions will create errors :) 
* <code>-depth 8</code>number of bits for color. 8bit depth <nowiki>==</nowiki> grey-scale 
* <code>-strip -background white -alpha off</code> removes alpha channel (opacity), and makes the background white 
* <code>output.tiff</code>in previous versions Tesseract only accepted images as tiffs, but currently more bitmap formats are accepted

OCR
 tesseract output.tiff -l eng output
Will generate the file output.txt
* -l is the option for language (English is the default)


==details==
===language===
Lists all tesseract languages available in your system.

 tesseract --list-langs

Select more than language
 tesseract output.tiff -l eng+spa output


==multipages==
Tiff files can be multi-page images. Hence if we use the prevoious  IM command to convert a PDF to a TIFF, if the PDF is multi page, so will be it TIFF. Which Tesseract should handle. 
<source lang="bash">
$ tesseract TypewriterArt.tiff TypewriterArt
Tesseract Open Source OCR Engine v3.03 with Leptonica
Page 1 of 8
Page 2 of 8
Page 3 of 8
</source>

Another option is providing Tesseract with a text file containing the path/filename to each image in sequence:

<source lang="bash">
p001.tiff
p002.tiff
p003.png
</source>

tesseract savedlist output


===hocr==
Tesseract 3.0x supports a hocr option, which creates [https://en.wikipedia.org/wiki/HOCR horc] file.

HOCR is an HTML+XML (XHTML) file consisting of recognized words and their coordinates.

It atomizes the OCRed text into text elements of different magnitude, such as:
* paragraph "ocr_par"
* line "ocr_line"
* word "ocrx_word"
 
<ref>‘HOCR - OCR Workflow and Output Embedded in HTML’. n.d. Accessed 11 January 2018. http://kba.cloud/hocr-spec/1.2/.
</ref>


==training==

Box file editor: [https://code.google.com/archive/p/moshpytt/downloads moshPyTT] for Tesseract v.3.0

See more Tesseract add-on in https://github.com/tesseract-ocr/tesseract/wiki/AddOns

== Artistic research ==

http://38.media.tumblr.com/04397537de7ab8e4fdaf8151e78c6bbb/tumblr_nekvu9mCc01tif66co1_250.png

[http://reverseocr.tumblr.com/ "Reverse OCR"]


==References==
<references/>