Pyocr is an optical character recognition (OCR) tool wrapper for python.
That is, it helps using OCR tools from a Python program.

Pyocr can be used as a wrapper for google's Tesseract-OCR
( http://code.google.com/p/tesseract-ocr/ ) or Cuneiform. It can read all image
types supported by the Python Imaging Library, including jpeg, png, gif, bmp, tiff,
and others. It also support bounding box data.

USAGE:
import Image
import sys
from pyocr import pyocr

tools = pyocr.get_available_tools()[:]
if len(tools) == 0:
    print "No OCR tool found"
    sys.exit(1)
print "Using '%s'" % (tools[0].get_name())
tools[0].image_to_string(Image.open('test.png'), lang='fra',
                         builder=TextBuilder())

DEPENDENCIES:
* Pyocr requires python 2.5 or later.
* You will need the Python Imaging Library (PIL).  Under Debian/Ubuntu, this is
  the package "python-imaging".
* Install an OCR:
  * tesseract-ocr from http://code.google.com/p/tesseract-ocr/ .
    You must be able to invoke the tesseract command as "tesseract".
    Python-tesseract is tested with Tesseract >= 3.01 only.
  * or cuneiform

INSTALLATION:
$ sudo python ./setup.py install

TESTS:
Tests are made to be run with the latest versions of Tesseract and Cuneiform.
the first test verifies that you're using the expected version.

COPYRIGHT:
Pyocr is released under the GPL v3.
tesseract.py:
  Copyright (c) Samuel Hoffstaetter, 2009
  Copyright (c) Jerome Flesch, 2011-2012
other files:
  Copyright (c) Jerome Flesch, 2011-2012
http://wiki.github.com/jflesch/python-tesseract