okralact
a multi-engine Open Source OCR training system
Rui Dong, Konstantin Baierer, Clemens Neudecker
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Slides: https://hackmd.io/@kba/SyiQKUCUH
Ocropus
kraken
calamari
tesseract
OCRopus
- @tmbdev since 2007 (ocropy: 2010)
- Standout features:
- often used, lots of documentation and wrappers (e.g. Ocrocis)
- CLI tools:
ocropus-nlbin,ocropus-gteditetc.
kraken
- @mittagessen since 2015
- Standout features:
- Clean codebase, documentation and interfaces
- CLI tools:
kraken binarize,ketos transcribeetc.
calamari
- @CHWick since 2018
- Standout features:
- Clean codebase, documentation and interfaces
- n-fold training and voting
tesseract
- @theraysmith since 1985 (LSTM: 2016)
- Standout features:
- Huge user and developer base
- Elaborate maintenance, testing, model generation etc.
Training
Basic Approach
- Produce line-based Ground Truth (GT)
- Feed into training engine:
- line text and image from GT
- neural network structure
- language model
Different Conventions (examples)
- File name and folder structure schemes
- Neural network setup
- Training stop conditions
- Log format
Case in Point: tesstrain (formerly known as ocrd-train)
- Started in 2018 as Makefile to make tesseract 4.0 training manageable
- Grown to include lots of optimizations
- Embraced by tesseract maintainers as of August 2019
Standardize!
Why?
- Who knows how
en-default.pyrnn.gzwas trained? - Synthetic data? Real line images? Both?
- How would
en-default.pyrnn.gzperform compared to Calamari trained on the same data? - Engines are evolving
so models must too
Ground Truth
- OCR-D has been developing GT specifications
- Training has different requirements:
- line-based
- data integrity is crucial
- metadata to track provenance
- => Engine-agnostic container format for line GT
Training
- Many parameters equivalent across engines => Common API
- Details matter => JSON Schema
- Track progress and performance uniformly
Evaluation
- Decouple evaluation from training
- Test snapshots of models by predicting GT
- Currently CER and WER
- Synergies with qurator-spk/dinglehopper, eddieantonio/ocreval and impactcentre/ocrevalUAtion
Models
- Uniform container format based on BagIt
- Include provenance and bibliographical metadata
- Previous work in kraken to build upon
Architecture
Caveat
- okralact - the software - is fully working but a prototype
- What we want to push with okralact
- engine-spanning conventions
- harmonized network structure specification
- better documentation and provenance of trained models
Tech stack
- Redis Queues for training and evaluation backed by Python workers
- Different JSON Schemas to model Common API and engine-specifics
- Python/Flask for a simple web interface
Engine-agnostic training interfaces:
possible necessary in everybody's interest
Let's do this!
Thank you!
- Okralact: https://github.com/OCR-D/okralact
- OCR-D GitHub Org: https://github.com/OCR-D
- OCR-D Specs and Documentation: https://ocr-d.github.io
- Chat with us: https://gitter.im/OCR-D/Lobby
okralact a multi-engine Open Source OCR training system Rui Dong, Konstantin Baierer, Clemens Neudecker Slides: https://hackmd.io/@kba/SyiQKUCUH
{"metaMigratedAt":"2023-06-15T00:06:25.162Z","metaMigratedFrom":"YAML","title":"okralact - a multi-engine Open Source OCR training system","breaks":false,"description":"Yeah.","slideOptions":"{\"theme\":\"blood\",\"spotlight\":{\"enabled\":false}}","contributors":"[{\"id\":\"e8137db5-d2e1-4125-8f51-e51a4ef3646b\",\"add\":9708,\"del\":3916},{\"id\":\"522e25fb-df8d-45d9-92fc-8ba16bd41dd1\",\"add\":60,\"del\":0}]"}