【Windows】tesseractでOCR

tesseract sample.png result -l jpn

何言つてんだよ! !
その崖っぷちが最髙のチヤンスなんだぜ ! !

まつおかしゅうぞう

> conda create -n ocr python=3.6
> conda info -e
# conda environments:
#
base                  *  c:\tools\Anaconda3
ocr                      c:\tools\Anaconda3\envs\ocr
> activate ocr
(ocr)> pip install 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.

(ocr)> python test.py
Will use tool 'Tesseract (sh)'
Available languages: eng, jpn
Will use lang 'eng'

from PIL import Image
import sys
sys.path.append('/path/to/dir')

import codecs
import pyocr
import pyocr.builders

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

# 画像から文字列を取得する
txt = tool.image_to_string(
    Image.open('sample2.png'),
    lang='jpn',
    builder=builder
)

# 文字列を書き出す
with codecs.open("result2.txt", 'w', encoding='utf-8') as file_descriptor:
    builder.write_file(file_descriptor, txt)

(ocr)> python img_to_txt.py

ー番になるつていつたよな?
日本ーなるつつつたよな!
ぬるま湯なんかつかつてんじゃねぇよお前! !

まつおかしゆうぞう