sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2025-07-02 01:10:35 +00:00
Code Issues Projects Releases Wiki Activity

Add description to hocrtotei

Browse Source
This commit is contained in:
Patrick Jentsch
2019-05-16 14:59:22 +02:00
parent b81ad4cc67
commit 46bb0efd14
2 changed files with 7 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ocr
View File

@ -29,13 +29,7 @@ from pyflow import WorkflowRunner
def parse_arguments():
parser = argparse.ArgumentParser(
'Performs OCR of (historical) documents utilizing OCRopus for \
preprocessing and Tesseract OCR for OCR. Available outputs are HOCR, \
PDF, shrinked PDF, and simple DTAbf (TEI P5 compliant). Software \
requirements: imagemagick, ocropus, pdftoppm, pdfunite, \
poppler-utils, pyflow, python2.7, python3.5, tesseract'
)
parser = argparse.ArgumentParser(description='Performs OCR of (historical) documents utilizing OCRopus for preprocessing and Tesseract OCR for OCR. Available outputs are hOCR, PDF, TEI compliant XML and raw text. Software requirements: imagemagick, ocropus, pdftoppm, pdfunite, poppler-utils, pyflow, python2.7, python3.5, tesseract')
parser.add_argument(
'-i',
dest='inputDirectory',