issues
search
UB-Mannheim
/
AustrianNewspapers
NewsEye / READ OCR training dataset from Austrian Newspapers (1864–1911)
15
stars
3
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Official Announcement: Release of the revised version according to the OCR-D Level 2 guidelines
#39
JKamlah
closed
9 months ago
6
Improve line images
#38
wollmers
opened
3 years ago
1
update Page-XML to sync with changes of line files.
#37
wollmers
closed
3 years ago
1
lexical spell check & visual confirmed
#36
wollmers
closed
3 years ago
0
vulgar fractions and lexical spellchecking (visually verified)
#35
wollmers
closed
3 years ago
1
J/I transcription in Fraktur
#34
wollmers
closed
3 years ago
4
Some other corrections
#33
wollmers
closed
3 years ago
1
update page XML files from txt files
#32
wollmers
closed
3 years ago
1
fix occasionally found wrong transcriptions
#31
wollmers
closed
3 years ago
1
GTCHeck: 180 Files, fix confusions and typos.
#30
JKamlah
closed
3 years ago
1
Line images with more than one line in GT data set
#29
stweil
opened
4 years ago
0
Rotated texts in GT data set
#28
stweil
opened
4 years ago
6
Fix confusions and typos.
#27
JKamlah
closed
4 years ago
1
spellchecks
#26
wollmers
closed
4 years ago
1
Normalise transcription; spellchecks
#25
wollmers
closed
4 years ago
1
spellcheck & vidit
#24
wollmers
closed
4 years ago
1
spellcheck & vidit part 1
#23
wollmers
closed
4 years ago
1
Info: current statistics
#22
wollmers
opened
4 years ago
0
unify circles, triangles, quads (remove Greek letters), remove tabs
#21
wollmers
closed
4 years ago
0
long-s and -/⸗ corrected with Fraktur heuristic & vidit
#20
wollmers
closed
4 years ago
1
Rotated Characters, Typesetting Errors
#19
wollmers
opened
4 years ago
1
check all lines containing ###, solve if possible, ~98 remain
#18
wollmers
closed
4 years ago
1
punctuation, some superscript numerals & others
#17
wollmers
closed
4 years ago
1
Missing line files (txt and png)
#16
wollmers
opened
4 years ago
3
long-s at begin of line rechecked from tesseract diff
#15
wollmers
closed
4 years ago
1
all sch should be correct now
#14
wollmers
closed
4 years ago
1
change 2c. to rotunda, and others found during correction
#13
wollmers
closed
4 years ago
1
Another bunch of long-s, fractions and ⸗ in Fraktur
#12
wollmers
closed
4 years ago
1
Many corrections and xml-update
#11
wollmers
closed
4 years ago
1
[GT Checked] Files: 1718. Fixed s,f and ſ confusions and some …
#10
JKamlah
closed
4 years ago
5
Discussion: Transcription of decimal dot in numbers
#9
wollmers
opened
4 years ago
0
line files not following the XML id pattern tl_\d+ are missing
#8
wollmers
opened
4 years ago
2
proofreading page ONB_aze_18950706_1
#7
wollmers
closed
4 years ago
1
Some easy fixes
#6
wollmers
closed
4 years ago
1
fix rotundas used for etc., one dozen '2c' remaining to check visually in context
#5
wollmers
closed
4 years ago
3
some manual fixes along grep -R ###
#4
wollmers
closed
4 years ago
1
Some PNGs in gt/train are truncated
#3
wollmers
opened
4 years ago
2
Deskew the line images?
#2
wollmers
opened
4 years ago
10
Question: Format of pull request
#1
wollmers
opened
4 years ago
5