Python と OCR を使用したドキュメント解析の完全なコード デモ (コードは添付)

# with pip
pip install python-poppler
# with conda
conda install -c conda-forge poppler

# READ AS IMAGE
import pdf2imagedoc = pdf2image.convert_from_path("doc_apple.pdf")
len(doc) #<-- check num pages
doc[0] #<-- visualize a page

# Save imgs
import osfolder = "doc"
if folder not in os.listdir():
 os.makedirs(folder)p = 1
for page in doc:
 image_name = "page_"+str(p)+".jpg"
 page.save(os.path.join(folder, image_name), "JPEG")
 p = p+1

pip install layoutparser torchvision && pip install "git+https://github.com/facebookresearch/detectron2.git@v0.5#egg=detectron2"

pip install "layoutparser[ocr]"

import layoutparser as lp
import cv2
import numpy as np
import io
import pandas as pd
import matplotlib.pyplot as plt

## load pre-trained model
model = lp.Detectron2LayoutModel(
 "lp://PubLayNet/mask_rcnn_X_101_32x8d_FPN_3x/config",
 extra_config=["MODEL.ROI_HEADS.SCORE_THRESH_TEST", 0.8],
 label_map={0:"Text", 1:"Title", 2:"List", 3:"Table", 4:"Figure"})
## turn img into array
i = 21
img = np.asarray(doc[i])
## predict
detected = model.detect(img)
## plot
lp.draw_box(img, detected, box_width=5, box_alpha=0.2,
 show_element_type=True)

## sort
new_detected = detected.sort(key=lambda x: x.coordinates[1])
## assign ids
detected = lp.Layout([block.set(id=idx) for idx,block in
 enumerate(new_detected)])## check
for block in detected:
 print("---", str(block.id)+":", block.type, "---")
 print(block, end='nn')

'''
{'0-Title': '...',
'1-Text': '...',
'2-Figure': array([[ [0,0,0], ...]]),
'3-Table': pd.DataFrame,
}
'''
def parse_doc(dic):
 for k,v in dic.items():
 if "Title" in k:
 print('x1b[1;31m'+ v +'x1b[0m')
 elif "Figure" in k:
 plt.figure(figsize=(10,5))
 plt.imshow(v)
 plt.show()
 else:
 print(v)
 print(" ")

# load model
model = lp.TesseractAgent(languages='eng')
dic_predicted = {}
for block in [block for block in detected if block.type in ["Title","Text"]]:
 ## segmentation
 segmented = block.pad(left=15, right=15, top=5,
 bottom=5).crop_image(img)
 ## extraction
 extracted = model.detect(segmented)
 ## save
 dic_predicted[str(block.id)+"-"+block.type] =
 extracted.replace('n',' ').strip()
# check
parse_doc(dic_predicted)

for block in [block for block in detected if block.type == "Figure"]:
 ## segmentation
 segmented = block.pad(left=15, right=15, top=5,
 bottom=5).crop_image(img)
 ## save
 dic_predicted[str(block.id)+"-"+block.type] = segmented
# check
parse_doc(dic_predicted)

for block in [block for block in detected if block.type == "Table"]:
 ## segmentation
 segmented = block.pad(left=15, right=15, top=5,
 bottom=5).crop_image(img)
 ## extraction
 extracted = model.detect(segmented)
 ## save
 dic_predicted[str(block.id)+"-"+block.type] = pd.read_csv(
 io.StringIO(extracted) )
# check
parse_doc(dic_predicted)

import tabula
tables = tabula.read_pdf("doc_apple.pdf", pages=i+1)
tables[0]