sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2024-12-26 05:04:17 +00:00
Code Issues Projects Releases Wiki Activity

Some cosmetics

Browse Source
This commit is contained in:
stephan 2020-02-17 14:59:34 +01:00
parent 880f0efcf9
commit c1f5252633
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
ocr
View File

@ -16,12 +16,17 @@ import os
import re import re
import sys import sys
from pyflow import WorkflowRunner from pyflow import WorkflowRunner
from zipfile import ZipFile
def parse_arguments(): def parse_arguments():
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description='Performs OCR of (historical) documents utilizing OCRopus for preprocessing and Tesseract OCR for OCR. The results are served as hOCR, PDF, raw text and TEI compliant XML files.\nSoftware requirements: imagemagick, ocropus, pdftoppm, pdfunite, poppler-utils, pyflow, python2.7, python3.5, tesseract' description='''Performs OCR of (historical) documents utilizing OCRopus
for preprocessing and Tesseract OCR for OCR. The results
are served as hOCR, PDF, raw text and TEI compliant XML
files.\n
Software requirements: imagemagick, ocropus, pdftoppm,
pdfunite, poppler-utils, pyflow, python2.7, python3.5,
tesseract'''
) )
parser.add_argument( parser.add_argument(
'-i', '-i',