This repository has been archived by the owner. It is now read-only.
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
327 lines (242 sloc) 8.35 KB


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

It has been tested only on GNU/Linux systems. It should also work on similar systems (*BSD, etc). It may or may not work on Windows, MacOSX, etc.

Supported OCR tools

  • Libtesseract (Python bindings for the C API)
  • Tesseract (wrapper: fork + exec)
  • Cuneiform (wrapper: fork + exec)


  • Supports all the image formats supported by Pillow, including jpeg, png, gif, bmp, tiff and others
  • Various output types: text only, bounding boxes, etc.
  • Orientation detection (Tesseract and libtesseract only)
  • Can focus on digits only (Tesseract and libtesseract only)
  • Can save and reload boxes in hOCR format
  • PDF generation (libtesseract only)


  • hOCR: Only a subset of the specification is supported. For instance, pages and paragraph positions are not stored.


sudo pip install pyocr  # Python 2.7
sudo pip3 install pyocr  # Python 3.X

or the manual way:

mkdir -p ~/git ; cd git
git clone
cd pyocr
make install  # will run 'python ./ install'



from PIL import Image
import sys

import pyocr

tools = pyocr.get_available_tools()
if len(tools) == 0:
    print("No OCR tool found")
# The tools are returned in the recommended order of usage
tool = tools[0]
print("Will use tool '%s'" % (tool.get_name()))
# Ex: Will use tool 'libtesseract'

langs = tool.get_available_languages()
print("Available languages: %s" % ", ".join(langs))
lang = langs[0]
print("Will use lang '%s'" % (lang))
# Ex: Will use lang 'fra'
# Note that languages are NOT sorted in any way. Please refer
# to the system locale settings for the default language
# to use.

Image to text

txt = tool.image_to_string('test.png'),
# txt is a Python string

word_boxes = tool.image_to_string('test.png'),
# list of box objects. For each box object:
#   box.content is the word in the box
#   box.position is its position on the page (in pixels)
# Beware that some OCR tools (Tesseract for instance)
# may return empty boxes

line_and_word_boxes = tool.image_to_string('test.png'), lang="fra",
# list of line objects. For each line object:
#   line.word_boxes is a list of word boxes (the individual words in the line)
#   line.content is the whole text of the line
#   line.position is the position of the whole line on the page (in pixels)
# Each word box object has an attribute 'confidence' giving the confidence
# score provided by the OCR tool. Confidence score depends entirely on
# the OCR tool. Only supported with Tesseract and Libtesseract (always 0
# with Cuneiform).
# Beware that some OCR tools (Tesseract for instance) may return boxes
# with an empty content.

# Digits - Only Tesseract (not 'libtesseract' yet !)
digits = tool.image_to_string('test-digits.png'),
# digits is a python string

Argument 'lang' is optional. The default value depends of the tool used.

Argument 'builder' is optional. Default value is builders.TextBuilder().

If the OCR fails, an exception pyocr.PyocrException will be raised.

An exception MAY be raised if the input image contains no text at all (depends on the OCR tool behavior).

Orientation detection

Currently only available with Tesseract or Libtesseract.

if tool.can_detect_orientation():
        orientation = tool.detect_orientation(
    except pyocr.PyocrException as exc:
        print("Orientation detection failed: {}".format(exc))
    print("Orientation: {}".format(orientation))
# Ex: Orientation: {
#   'angle': 90,
#   'confidence': 123.4,
# }

Angles are given in degrees (range: [0-360[). Exact possible values depend of the tool used. Tesseract only returns angles = 0, 90, 180, 270.

Confidence is a score arbitrarily defined by the tool. It MAY not be returned.

detect_orientation() MAY raise an exception if there is no text detected in the image.

Writing and reading text files


import codecs
import pyocr

tool = pyocr.get_available_tools()[0]
builder =

txt = tool.image_to_string('test.png'),
# txt is a Python string

with"toto.txt", 'w', encoding='utf-8') as file_descriptor:
    builder.write_file(file_descriptor, txt)
# toto.txt is a simple text file, encoded in utf-8


import codecs

builder =
with"toto.txt", 'r', encoding='utf-8') as file_descriptor:
    txt = builder.read_file(file_descriptor)
# txt is a Python string

Writing and reading hOCR files


import codecs
import pyocr

tool = pyocr.get_available_tools()[0]
builder =

line_boxes = tool.image_to_string('test.png'),
# list of LineBox (each box points to a list of word boxes)

with"toto.html", 'w', encoding='utf-8') as file_descriptor:
    builder.write_file(file_descriptor, line_boxes)
# toto.html is a valid XHTML file


import codecs

builder =
with"toto.html", 'r', encoding='utf-8') as file_descriptor:
    line_boxes = builder.read_file(file_descriptor)
# list of LineBox (each box points to a list of word boxes)

Generating PDF file from an image

With libtesseract >= 4, it's possible to generate a PDF from an image:

import PIL.Image
import pyocr

    "output_filename"  # .pdf will be appended

Beware this code hasn't been adapted to libtesseract 3 yet.


  • PyOCR requires python 2.7 or later. Python 3 is supported.
  • You will need Pillow or Python Imaging Library (PIL). Under Debian/Ubuntu, Pillow is in the package python-pil (python3-pil for the Python 3 version).
  • Install an OCR:
    • libtesseract ('libtesseract3' + 'tesseract-ocr-<lang>' in Debian).
    • or tesseract-ocr ('tesseract-ocr' + 'tesseract-ocr-<lang>' in Debian). You must be able to invoke the tesseract command as "tesseract". PyOCR is tested with Tesseract >= 3.01 only.
    • or Cuneiform


make check  # requires pyflake8
make test  # requires tox

Tests are made to be run with the latest versions of Tesseract and Cuneiform. the first tests verify that you're using the expected version.

To run the tesseract tests, you will need the following lang data files:

  • English (tesseract-ocr-eng)
  • French (tesseract-ocr-fra)
  • Japanese (tesseract-ocr-jpn)

OCR on natural scenes

If you want to run OCR on natural scenes (photos, etc), you will have to filter the image first. There are many algorithms possible to do that. One of those who gives the best results is Stroke Width Transform.


Applications that use PyOCR

If you know of any other applications that use Pyocr, please tell us :-)


PyOCR is released under the GPL v3+. Copyright belongs to the authors of each piece of code (see the file AUTHORS for the contributors list, and git blame to know which lines belong to which author).