LoginSignup
49
70

More than 5 years have passed since last update.

PythonでOCR

Last updated at Posted at 2017-10-21

TL;DR

tesseractをpyocrから呼び出して使う方法。

OCRツールを入れる

今回はtesseractを入れる。
こちらの記事から各環境向けの入れ方を参照すること。
https://github.com/tesseract-ocr/tesseract/wiki

Windows向け

執筆時最新版は4.0.0αのWindows Installer made with MinGW-w64

Choose Componentsにて、Additional language dataからJapaneseを選択する。

インストール後、"C:\Program Files (x86)\Tesseract-OCR"をPathに追加する。

pyocrを入れる

pip install pyocr

Windowsの場合は、事前にAnacondaなどを入れておくと楽。

pyocrからtesseractを呼び出せるか確認

pyocrの公式ページのコードで確認する。
https://github.com/openpaperwork/pyocr

from PIL import Image
import sys

import pyocr
import pyocr.builders

tools = pyocr.get_available_tools()
if len(tools) == 0:
    print("No OCR tool found")
    sys.exit(1)
# 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.
Output(Example)
Will use tool 'Tesseract (sh)'
Available languages: eng, equ, jpn, osd
Will use lang 'eng'

文字認識

認識したい画像( iroha.png )

iroha.png

from PIL import Image
import sys

import pyocr
import pyocr.builders

tools = pyocr.get_available_tools()
if len(tools) == 0:
    print("No OCR tool found")
    sys.exit(1)
# 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.

txt = tool.image_to_string(
    Image.open('iroha.png'),
    lang="jpn",
    builder=pyocr.builders.TextBuilder(tesseract_layout=6)
)
print( txt )
# txt is a Python string

Output
い ろ は に ほ へ と ち り ぬ

覚え書き

解像度低い文字画像だと認識上手くいかない。少なくとも、slackのemojiの解像度じゃダメだった。

参考

OCRツール「Tesseract OCR」をインストールしてPythonで使う http://73spica.tech/blog/tesseract_for_python/

49
70
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
49
70