zuphilip / ocropus-git Goto Github PK

##Version 0.4
## compile on ubuntu 14.04
scons
sudo scons install
ocropus


OCRopus - open source document analysis and OCR system (www.ocropus.org)

Version 0.3 (2008-10-15)


--------------------------------------------------------------------------------
Building OCRopus (quick start)
--------------------------------------------------------------------------------
1) make sure you have these packages installed (current Ubuntu/Debian versions should work):
    libpng (with headers)
    libjpeg (with headers)
    libtiff (with headers)

2) install iulib from http://code.google.com/p/iulib

3) install a current version of tesseract from the Subversion repository
    (http://code.google.com/p/tesseract-ocr)

4) from the release directory, run
    ./configure
    make
    sudo make install

Please refer to the file INSTALL for more help on building OCRopus from source.


--------------------------------------------------------------------------------
Executing OCRopus
--------------------------------------------------------------------------------
After successfully building and installing OCRopus you can use "ocroscript"
to recognize document images.
Try e.g.
    ocroscript recognize data/pages/alice_1.png


--------------------------------------------------------------------------------
Documentation
--------------------------------------------------------------------------------
Please refer to http://www.ocropus.org for the most recent documentation.


--------------------------------------------------------------------------------
Background
--------------------------------------------------------------------------------
OCRopus is a state-of-the-art document analysis and OCR system, featuring
    * pluggable layout analysis,
    * pluggable character recognition,
    * statistical natural language modeling and
    * multi-lingual capabilities.
OCRopus development is sponsored by Google and is initially intended for
high-throughput, high-volume document conversion efforts. We expect that
it will also be an excellent OCR system for many other applications.

OCRopus is mainly based on research projects of Thomas Breuel and the Image
Understanding and Pattern Recognition (IUPR) group of the German Research
Center for Artificial Intelligence (DFKI) located in Kaiserslautern, Germany.

OCRopus uses data structures and algorithms from iulib - the open source 
Image Understanding Library (http://code.google.com/p/iulib/) which has
been part of OCRopus until June 2008.


--------------------------------------------------------------------------------
Online Resources
--------------------------------------------------------------------------------
Homepage:
    http://www.ocropus.org

Forum / Mailinglist:
    http://groups.google.com/group/ocropus

Public Issue Tracker:
    http://code.google.com/p/ocropus/issues

OCRopus is made by IUPR:
    http://www.iupr.org

IUPR is a part of DFKI:
    http://www.dfki.de

hOCR Output Format:
    http://docs.google.com/View?docid=dfxcv4vc_67g844kf