・ Https://gammasoft.jp/blog/tesseract-ocr-install-on-windows/ -Execute tesseract-ocr-w64-setup-v5.0.0-alpha.20200223.exe -Additional script data (download): Check Japanese script and Japanese vertical script ・ Additional language data (download): Check Javanese, Japanese and Japanese (vertical)
・ Https://poppler.freedesktop.org/ ・ Download the poppler folder
・ Tesseract-OCR ・ Poppler-0.67.0 \ bin Add the above to your PATH
import os
from PIL import Image
from matplotlib import pyplot as plt
import cv2
from pdf2image import convert_from_path
import pyocr
import pyocr.builders
import sys
import pandas as pd
import time
import numpy as np
import glob
import shutil
#OCR tool itself
def OCR_read(PIL_data):
tools = pyocr.get_available_tools()
if len(tools) == 0:
print("No OCR tool found")
sys.exit(1)
tool = tools[0]
txt = tool.image_to_string( #Specify the OCR target, language, and options here.
PIL_data,
lang='jpn',
builder=pyocr.builders.TextBuilder(tesseract_layout=6)
)
txt1 = txt.replace(' ','').replace('\n','').replace('|','')
return txt1
#Convert PDF file to image
def pdftoimage(work_directory, path1):
images = convert_from_path(path1)
i = 0
for image in images:
print("Making work{}.png ...".format(i))
image.save(work_directory +"/Output_folder/"+ "work{}.png ".format(i))
i += 1
imax =i
return imax
Recommended Posts