Page segmentation and segmentation evaluation
Project description
ocrd_segment
This repository aims to provide a number of OCR-D compliant processors for layout analysis and evaluation.
Installation
In your Python virtual environment, run:
pip install ocrd_segment
Usage
Contains processors for various tasks:
- exporting segment images (including results from preprocessing like cropping/masking, deskewing, dewarping or binarization) along with polygon coordinates and metadata:
- ocrd-segment-extract-pages (for pages, also exports MS-COCO format)
- ocrd-segment-extract-regions (for regions)
- ocrd-segment-extract-lines (for lines, also exports text and .xlsx)
- ocrd-segment-extract-words (for words, also exports text)
- ocrd-segment-extract-glyphs (for glyphs, also exports text)
- importing layout segmentations from other formats:
- ocrd-segment-from-masks (for mask/label images, i.e. semantic segmentation)
- ocrd-segment-from-coco (for MS-COCO annotation)
- post-processing or repairing layout segmentations:
- ocrd-segment-repair (validity and consistency of coordinates, reducing overlaps/redundancy between neighbours, shrinking regions to the alpha shape of their lines)
- ocrd-segment-project (remake segment coordinates into the concave hull / alpha shape of their constituents)
- ocrd-segment-replace-original (rebase all segments on cropped+deskewed border frame as new full page)
- ocrd-segment-replace-page (2 input fileGrps; overwrite segmentation below page of first fileGrp by all segments of second fileGrp, rebasing all coordinates; "inverse" of
replace-original
)
- comparing different layout segmentations:
- ocrd-segment-evaluate :construction: (2 input fileGrps; align, compare and evaluate page segmentations; early stage)
- page-segment-evaluate (same with standalone CLI)
- pattern-based segmentation (input file groups N=1, based on a PAGE template, e.g. from Aletheia, and some XSLT or Python to apply it to the input file group)
ocrd-segment-via-template
:construction: (unpublished)
- data-driven segmentation (input file groups N=1, based on a statistical model, e.g. Neural Network)
ocrd-segment-via-model
:construction: (unpublished)
For detailed behaviour, see --help
on each processor CLI.
For detailed description on input/output and parameters, see ocrd-tool.json or --dump-json
on each processor CLI.
Testing
None yet.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ocrd_segment-0.1.17.tar.gz
(46.2 kB
view hashes)
Built Distribution
Close
Hashes for ocrd_segment-0.1.17-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a076ee5f025c1d9970bcd21168598f8f8ffa22b5d276b52f52c5fed1b4253476 |
|
MD5 | 50f18c68ca031e3938f8bac8f89d8eec |
|
BLAKE2b-256 | 2052fdf74d32eb59f4e06d9eb1b5670c3ae7b0cf63d4f8451286e10392eea500 |