Gerber, Mike
0c9e1f13c7
🐛 Sort predictions in exactly the same way to make sure we are correctly removing spaces
5 years ago
Gerber, Mike
d2c843aa3f
📦 v0.0.5
5 years ago
Gerber, Mike
cd8f6a5fcb
🐛 Use line id for debug message
5 years ago
Gerber, Mike
5b6d8b3f41
🐛 Build line text on our own
...
Calamari does whitespace post-processing on prediction.sentence, while
it does not do the same on prediction.positions. Do it on our own to
have consistency.
Fixes GH-37.
5 years ago
Gerber, Mike
4508e3ec47
📦 v0.0.4
5 years ago
Gerber, Mike
b802b4deaf
✨ Allow configuring a cut off confidence value for glyph alternatives
5 years ago
Gerber, Mike
ef3fb44fb5
✨ Allow controlling of output hierarchy level, e.g. only line, not words+glyphs
5 years ago
Gerber, Mike
6f4736f8e4
✨ Do word segmentation as expected by OCR-D PAGE specs
5 years ago
Gerber, Mike
0f9c94e7dc
🐛 Start with TextEquiv index=1 to adhere to OCR-D PAGE conventions
...
https://ocr-d.github.io/page#multiple-textequivs
5 years ago
Gerber, Mike
909632493b
🚧 Add future TODOs
5 years ago
Gerber, Mike
3149e1d9e0
📝 unwanted()
5 years ago
Gerber, Mike
91cca1e1b8
📝 Document why we are using Unicode text segmentation to produce word results
5 years ago
Gerber, Mike
2650189910
🧹 Add whitespace
5 years ago
Gerber, Mike
f75426060e
🧹 Remove debugging print
5 years ago
Gerber, Mike
decaa7b69f
🎨 Use polygon_from_x0y0x1y1 to build word/glyph polygon
5 years ago
Gerber, Mike
2ccfc7b195
🎨 Set vim textwidth
5 years ago
Gerber, Mike
507bc1ce5e
✨ Include proper word + glyph segmentation
5 years ago
Gerber, Mike
24532f693a
🚧 Use character positions as word segmentation
5 years ago
Gerber, Mike
49b6dfe735
🧹 Clean up trailing whitespace
5 years ago
Gerber, Mike
95281f3d29
✨ Add metadata about the recognition operation w/ parameter info
5 years ago
Gerber, Mike
dc38f0ee51
🎨 Use TOOL constant convention from the other OCR-D processors
5 years ago
103b1d7671
remove existing annotation below the line level to avoid inconsistency
5 years ago
e34998d58f
📝 readme, makefile, synopsis for cli
...
Conflicts:
Makefile
README.md
requirements.txt
5 years ago
b54ccf90f7
smoke test, circle ci
...
Conflicts:
Makefile
ocrd_calamari/__init__.py
5 years ago
Mike Gerber
afe6eec5a2
Merge pull request #16 from OCR-D/fix-version
...
pass version to processor base constructor, fix #14
5 years ago
0fcc5c1f79
pass version to processor base constructor, fix #14
5 years ago
Gerber, Mike
2597c93211
📦 v0.0.3 – To fix version inconsistency
5 years ago
Gerber, Mike
c4d52ee55b
📝 ocrd-tool.json: Add parameter descriptions
5 years ago
Gerber, Mike
6d2e15b623
🐛 Overwrite text if it exists
5 years ago
Gerber, Mike
31bdf3e425
⬆ Use image_from_segment instead of deprecated resolve_image_as_pil
5 years ago
Gerber, Mike
e805f1f900
🐛 Make ocrd_calamari a proper Python package to fix setup.py
5 years ago
Gerber, Mike
ebf0d53640
🚧 Do not hardcode used models
5 years ago
Gerber, Mike
8cfb075a6d
🚧 Remove unused parameters
5 years ago
Gerber, Mike
0498f9551e
🚧 Update higher TextEquiv levels
5 years ago
Gerber, Mike
2561b67891
🚧 Remove output_dir parameter as we are not outputting to text files
5 years ago
Gerber, Mike
319ce3a467
🚧 s/Ocr/Recognize
5 years ago
Gerber, Mike
611371fa2c
🚧 Use correct URL
5 years ago
Gerber, Mike
64794363d8
🚧 Use voter from JSON config
5 years ago
Gerber, Mike
67aa3db357
🚧 Remove unused import
5 years ago
Gerber, Mike
3b02da8da2
🚧 Set TensorFlow minimum log level
5 years ago
Gerber, Mike
4df04ac6d7
🚧 Update to ocrd >= 1.0.0b11
5 years ago
Gerber, Mike
f62332223b
🚧 Save results in the workspace
5 years ago
Gerber, Mike
b9e38487bd
🚧 Extract a method to resolve an image as a Numpy array
5 years ago
Gerber, Mike
dbe43e2316
🚧 Process lines
5 years ago
2ebf3c0e00
.
6 years ago
Robert Sachunsky
Konstantin Baierer