Robert Sachunsky
Robert Sachunsky
I'd also like to formalize the dependencies in proper setup.py distutils fashion...
If I follow the installation steps currently in the README, I get the following from the last `pip` command (i.e. when installing `layout-parser` a second time, after installing detectron2): ```...
In 355aaf9cdfb28fb3b9df9d08d7392b0ac342b425 @unhammer added a C++ constructor variant to `HfstInputStream` to initialize from a `std::istream`. This opens the possibility to use an `std::istringstream` too, e.g. when one has a OpenFST...
The [documentation](https://github.com/hfst/hfst/blob/1b6016897048d4afd77d3468659a67ae1dac56c5/libhfst/src/HfstTransducer.h#L1226) of `HfstTransducer::prune()` says: > /** \brief Make transducer coaccessible. */ And [similarly](https://github.com/hfst/hfst/blob/1b6016897048d4afd77d3468659a67ae1dac56c5/python/docstrings.i#L1484) for Python bindings. However, in fact that function **does** prune, and even with weight threshold `One()`,...
After installing `libcgal-dev` and its dependents, if I do pip install -e scikit-geometry then compilation fails like this: ``` Obtaining file:///data/ocr-d/origami/scikit-geometry Collecting pybind11>=2.3 Using cached pybind11-2.6.2-py2.py3-none-any.whl (191 kB) Installing collected...
If I use `ketos linegen` with the `--legacy` option, I currently get: ``` File "kraken/ketos.py", line 933, in line_generator im = linegen.ocropy_degrade(im) File "kraken/linegen.py", line 271, in ocropy_degrade (sigma, ssigma,...
Sometimes the input comes with DPI 600 or beyond. It seems to me this makes eynollah become much slower. Larger resolution might be needed for newspapers, but there is always...
On [this image](https://digital.slub-dresden.de/data/kitodo/Brsfded_39946221X-18560530/Brsfded_39946221X-18560530_tif/jpegs/00000002.tif.original.jpg), eynollah produces polygons that are invalid: ``` ERROR processor.ExtractPages - Page "PHYS_0002" ImageRegion "r91" Self-intersection[2151 3197] ERROR processor.ExtractPages - Page "PHYS_0002" ImageRegion "r92" Self-intersection[1605 99] ``` The...
The reading order detection capabilities of eynollah look pretty amazing AFAICS – if viewed through the glasses of PageViewer. But it is noteworthy that the actual representation for PAGE-XML does...
I know OCR-D integration is still underway, but just wanted to bring to attention that OCR-D currently lacks a neural (or in fact, any useable) cropping tool, and thus it...