kba

# tei2textpages.py
import lxml.etree as ET
import sys
import re

tei_file = sys.argv[1]

with open(tei_file, 'r') as f:
    tei_xml = f.read()
    tei_xml = re.sub(r'<\?xml version="1.0" encoding="UTF-8"\?>', '', tei_xml)

kba

Fix imageFilename in PAGE

sed -i 's,imageFilename=",imageFilename="page/",' page/*.xml

Initiate mets.xml

ocrd workspace init

kba

Typische OCR-Fehler

       1        0   {A}-{H} 
       1        0   {h}-{b} 
       1        0   {l}-{i} 
       1        0   {n}-{u} 
       1        0   {n}-{v} 
       1        0   {n}-{y} 
 1 0 {t}-{k} 

kba

#!/bin/bash

ocrd () {
        "C:/Users/kb/AppData/Local/Programs/Python/Python39/Scripts/ocrd.exe" "$@" |tr -d '\r'
}
layouteval () {
    set -x
        "/cygdrive/c/Users/kb/Downloads/LayoutEvalCmd_1-9-106/LayoutEvalCmd 1.9/layoutevalcmd-1-9-106.exe" \
                -printWarnings \
                -csvValues \

kba

#!/bin/bash                                                                                                                           
set  -e                                                                                                                               
                                                                                                                                      
ADD_TO_WORKSPACE=true                                                                                                                 
INPUT_FILE_GROUP=OCR-D-OCR-TESS                                                                                                       
OUTPUT_FILE_GROUP=TSV                                                                                                                 
DIRECTORY=$PWD                                                                                                                        
PPN=                                                                           

kba

#!/usr/bin/env bash
# reset environment variables that could interfere with normal usage
unset GREP_OPTIONS
# put all utility functions here

# make a temporary file
git_extra_mktemp() {
    mktemp -t "$(basename "$0")".XXXXXXX
}

kba

time ocrd process --overwrite "tesserocr-segment -P find_tables true -I OCR-D-IMG -O TESS" -g PHYS_0020
12:45:37.784 INFO ocrd.task_sequence.run_tasks - Start processing task 'tesserocr-segment -I OCR-D-IMG -O TESS -p '{"find_tables": true, "dpi": 0, "padding": 4, "shrink_polygons": false, "block_polygons": false, "find_staves": false, "sparse_text": false}''
12:45:38.758 INFO processor.TesserocrSegment - INPUT FILE 0 / PHYS_0020
12:45:38.835 INFO processor.TesserocrSegment - Page 'PHYS_0020' images will use 300 DPI from image meta-data
12:45:38.835 INFO processor.TesserocrSegment - Processing page 'PHYS_0020'
libpng warning: iCCP: profile 'ICC Profile': 'desc': ICC profile tag start not a multiple of 4
libpng warning: iCCP: profile 'ICC Profile': 'rXYZ': ICC profile tag start not a multiple of 4
libpng warning: iCCP: profile 'ICC Profile': 'gXYZ': ICC profile tag start not a multiple of 4
libpng warning: iCCP: profile 'ICC Profile': 'bXYZ': ICC profile tag start not a multiple of 4
libpng warning: iCCP: prof

kba

<?xml version="1.0" encoding="UTF-8"?>
<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xlink="http://www.w3.org/1999/xlink" xsi:schemaLocation="info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/v2/premis-v2-0.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-6.xsd http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/version17/mets.v1-7.xsd http://www.loc.gov/mix/v10 http://www.loc.gov/standards/mix/mix10/mix10.xsd">
  <mets:metsHdr CREATEDATE="2017-11-30T16:18:26">
    <mets:agent OTHERTYPE="SOFTWARE" ROLE="CREATOR" TYPE="OTHER">
      <mets:name>DFG-Koordinierungsprojekt zur Weiterentwicklung von Verfahren der Optical Character Recognition (OCR-D)</mets:name>
      <mets:note>OCR-D</mets:note>
    </mets:agent>
    <mets:agent TYPE="OTHER" OTHERTYPE="SOFTWARE" ROLE="OTHER" OTHERROLE="preprocessing/optimization/binarization">
      <mets:name>ocrd-cis-ocropy-binarize v0.1.5</mets:name>
      <mets:note xmlns: