sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2025-01-29 18:09:01 +00:00
Code Issues Projects Releases Wiki Activity

Remove comments

Browse Source
This commit is contained in:
Patrick Jentsch 2019-06-11 14:18:46 +02:00
parent 6f6d6e809e
commit 1a3d7175fe
1 changed files with 0 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
ocr
View File

@ -18,16 +18,6 @@ import sys
from pyflow import WorkflowRunner
''' TODO:
' Implement --end-page: Last page to ocr
' Implement --memMb: Total amount of memory (RAM) available for this workflow.
' Default: 2048 * n_cores
' Implement --rotate: Rotate pages from input (90, 180, 270)
' Implement --split-pages: Split pages in half after possible rotation
' Implement --start-page: First page to ocr
'''
def parse_arguments():
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'