Robert Sachunsky

OCR. OCR Models and Training Data Sorbian languages in Latin and Fraktur

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

page-dewarp. Document image dewarping library using a cubic sheet model

sbb_ocr_conf_eval. Python

pagexml-mets-viewer. Web app to upload and display multiple PageXML files

awesome-ocr.

DocLayout-YOLO. DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

DocTr. The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

ocrd_paddleocr. OCR-D integration for PaddleOCR

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

ocrd_party. OCR-D processor for the party text recognizer

ocrd_yolo. OCR-D wrapper for yolo based on the ocrd_detectron2 wrapper

sbb_binarizer_pytorch_converter. Python

mlm-scoring. Python library & examples for Masked Language Model Scoring (ACL 2020)

bytellama. A llama with octet tokenization

HTRMoPo. Schemas for repositories of HTR/OCR models

party. Page-wise text recognition with lower-supervision line data models

DeepSeek-V3. Python

DewarpNet. Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)

tei-publisher-app. The main TEI Publisher app

Projects. Projects of Mannheim University Library

ocr-model-catalogue. This repository contains a collection of layout analysis and text recogntion models.

ocapy. OCR Confidence Analysis script written in python

pdftotree. :evergreen_tree: A tool for converting PDF into hOCR with text, tables, and figures being recognized and preserved.

dach-gt. Ground truth and full text for selected prints of German libraries

DHd2024-demo. Shell

Kitodo-OCR-Docker. Dockerfile

loghi. Loghi is a comprehensive toolkit designed for Handwritten Text Recognition (HTR) and Optical Character Recognition (OCR), offering an accessible approach to transcribing historical documents and training models for specialized needs.

olahd_backend. Project repository for the backend module of OCR-D Implementation Project OLA-HD

olahd_user_frontend. Project repository for the frontend module of OCR-D Implementation Project OLA-HD

gt_structure_all. Python

awesome-ocr. Links to awesome OCR projects

dta-tools. Tools used in the project "Deutsches Textarchiv"

llama.cpp. LLM inference in C/C++

tesstrain. Train Tesseract LSTM with make

github-cheat-sheet. A list of cool features of Git and GitHub.

gt-management-dhd-2024. Slides and materials for the GT workshop at DHd 2024

GT-commentaries-layout. Ground truth data for Page Layout Analysis of Historical Classical Commentaries.

gt_structure_text. The OCR-D Ground Truth text and structure corpus was created between 2015 -2017. In the years since 2017, this corpus has been further curated and supplemented with metadata where appropriate. The corpus includes page XML files within annotations of the text and structure include.

frat. Fast Rectangle Annotation Tool

ulb-groundtruth-eval-odem-other. OCR Groundtruth ULB VD18 - OCR-D Phase III

ulb-groundtruth-eval-odem-ger. OCR Grountruth ULB VD18 German Fraktur - OCR-D Phase III

ulb-groundtruth-eval-odem-lat. OCR Groundtruth ULB VD18 Latin - OCR-D Phase III

gt_structure_dtaText. Batchfile

ddblabs-ometha. A fast and resilient OAI PMH Harvester with TUI and CLI and support for automation.

slub_digitalcollections. Templates, Styles and Configuration for Kitodo.Presentation based Digital Collections by SLUB Dresden

ocrd-demo-mets-server. Makefile

calamari. Line based ATR Engine based on OCRopy

ocrd-workflows. Shell

YALTAi. You Actually Look Twice At it

sampo. A shell script API server for running your shell scripts.

jdeskew. ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation

imgtabdet. Tool that tries to find line grids (i.e. a table) in an image

buildg. Interactive debugger for Dockerfile, with support for IDEs (VS Code, Emacs, Neovim, etc.)

gt-guideline-examples.

gt-repo-template. A template for creating a ground truth repo with the various functions and features: such as metadata creation, data analysis and presentation.

tei2hocr. XSLT Stylesheet to convert TEI OCR data to HOCR

ocr-conversion. Conversions between various OCR formats

ocrd-webapi-implementation. Python

Docker-layout-OHG. Shell

Docker-htr-OHG. Docker image that isolates and automates the use of htr tools for the OHG dataset.

laypa. Layout analysis to find layout elements in documents (similar to P2PaLA)

textract2page. Convert AWS Textract JSON to PRImA PAGE XML

hpc-rocket. Python

quipucamayoc. dev repo for article

Removing-Shadows-from-Images-of-Documents-by-Steve-Bako. This is the source code from "Removing Shadows from Images of Documents" by Steve Bako , Soheil Darabi, Eli Shechtman, Jue Wang, Kalyan Sunkavalli, and Pradeep Sen

codon. A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

Layout2Graph. An official implementation of paper "Paragraph2Graph: A Language-independent GNN-based framework for layout analysis"

deepdoctection. A Repo For Document AI

doctr. docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

DocLayNet. DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

PaddleDetection. Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Historical-document-layout-analysis. Python

gt_corpus_benchmark. This repo provides a collection of ground truth data. The collection was compiled under different aspects (complexity of the layouts and use of the fonts). The individual data are also characterized by metadata. The metadata is based on the labeling scheme of OCR-D/PrimaLab.

paperless-ngx. A community-supported supercharged document management system: scan, index and archive all your documents

wf_server_nf_script. Nextflow

ocrd_trocr. OCR-D processor for TrOCR

ocrd_froc. Python

CITlabErrorRate. tool to calculate quality of HTR/ATR, KWS, and Text2Image

ocreval. Update of the ISRI Analytic Tools for OCR Evaluation with UTF-8 support

METS-schema. METS 1.x and METS 2 schemas

digital-derivans. Derive new digitals from existing ones

NodeFlow. An Editor for creating simple or complex OCR workflows

newspaper-navigator. Jupyter Notebook

ICA_for_demixing_images. Python

bombers_baedeker. Weiterführung der ersten, prototypischen Vorgehensweise bei der XMLisierung und Extraktion von Entitäten aus dem zweibändigen Werk „Bomber's Baedeker“

Awesome-Image-Inpainting. A curated list of image inpainting and video inpainting papers and resources

CascadeTabNet. This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"

reichsanzeiger-nlp. Reichsanzeiger-NLP: NER/NEL corpus for the German historical newspaper "Deutscher Reichsanzeiger und Preußischer Staatsanzeiger" (1819–1939)

scorep_binding_python. Allows tracing of python code using Score-P

docstruct. Document structure detection from PAGE-XML to METS-XML

download-gitter.im-chat. tiny tool to download gitter.im chat

soldatenbriefe. Corpus data for collection “Soldatenbriefe des 18. und 19. Jahrhunderts”

gt-MufiLevelRules. OCR-D-Level-Rules can be created automatically with gt-MufiLevelRules from the encodings published by MUFI: The Medieval Unicode Font Initiative.

eynollah. Document Layout Analysis

OtoN_Converter. Converter from basic OCRD process workflow to Nextflow workflow script

hyperlearn. 2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

reichsanzeiger-gt. Ground truth for German newspaper "Deutscher Reichsanzeiger und Preußischer Staatsanzeiger" (1819–1945)

ocr-util. Evaluate data from mass digitalization workflows

ddb-metadata-schematron-validation. Schematron-Validierungen der Fachstelle Bibliothek der Deutsche Digitalen Bibliothek

ddev-dfgviewer. DDEV Development System for the DFG-Viewer

snakeviz. An in-browser Python profile viewer

tiler. N-dimensional NumPy array tiling and merging with overlapping, padding and tapering

quiver-back-end. The back end of the OCR-D quality dashboard webapp.

pero-enhance. Python

hsp-erfassung. TypeScript

hsbcala. train Calamari models for Upper Sorbian (Fraktur and Antiqua) prints on HPC

pero-ocr. Python

fix-perspective. C++

blitzDrt. Tool to correct perspective distortion. Does not correct verticals (column separators, table lines) yet. Uses Blitz++ library.

docformer. Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)

pytesstrain. Python tools for Tesseract OCR training

citlab-article-separation-new. Modules used for separating articles in (historical) newspapers and similar documents. This repository is part of the European Union's Horizon 2020 project NewsEye. For more information about the project see https://www.newseye.eu/.

ddblabs-iiimets. IIIF to METS/MODS conversion script

edx-lint. Custom tooling for pylint and other repo management tools

pd3f. 🏭 PDF text extraction pipeline: self-hosted, local-first, Docker-based

ocrd_manager. frontend for ocrd_controller and adapter towards ocrd_kitodo

alphashape. Toolbox for constructing alpha shapes.

OPERANDI_TestRepo. This is the OPERANDI project's test repository.

yt-dlp. A feature-rich command-line audio/video downloader

ocrd_kitodo. Docker integration of Kitodo.Production and OCR-D

pyhunspell. (Official repo for pypi package) Python bindings for the Hunspell spellchecker engine

ocrd_controller. Path to network implementation of OCR-D

docker-openssh-server. Dockerfile

ocrd_page2tei. OCR-D wrapper for page2tei

page2tei. XSLT

layout-model-training. The scripts for training Detectron2-based Layout Models on popular layout analysis datasets

magnitude. A fast, efficient universal vector embedding utility package.

ocrmultieval. Extensible evaluation of (intermediate) results of an OCR workflow

dfg-viewer. The DFG Viewer is a free web service for browsing digitized books from remote library repositories in a rich and dynamic environment.

PaddleOCR2Pytorch. PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

ocrd_detectron2. OCR-D wrapper for detectron2 based segmentation models

simple-docstrum. A step-by-step C# implementation of the Docstrum algorithm

carolineminuscule-groundtruth. OCR ground truth for Caroline Miniscule

BoundaryNet. BoundaryNet - A Semi-Automatic Layout Annotation Tool

glosat_table_dataset. GloSAT Historical Measurement Table Dataset

Order_Relation_Operator. Learning to Sort Handwritten Text Lines in Reading Order through Estimated Binary Order Relations

ReadingBank. ReadingBank: A Benchmark Dataset for Reading Order Detection

awesome-document-understanding. A curated list of resources for Document Understanding (DU) topic

DocBank. DocBank: A Benchmark Dataset for Document Layout Analysis

docsa. SLUB Document Classification and Similarity Analysis

LuigiNLP. A workflow system for Natural Language Processing.

openaudiosearch. Open Audio Search

vosk-api. Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

ocrd_vandalize. Demo processor to illustrate OCR-D Python API

jc. CLI tool and python library that converts the output of popular command-line tools, file-types, and common strings to JSON, YAML, or Dictionaries. This allows piping of output to tools like jq and simplifying automation scripts.

workflow-configuration. a makefilization for OCR-D workflows, with configuration examples

transkribus-to-prima. Convert Transkribus PAGE-XML to standard PAGE-XML

teihub. Automated listing of repos in GitHub with XML files containing teiHeader. Find a project using TEI today!

dtabf. DTA Base Format (DTABf)

AletheiaTools. AletheiaTools is a collection of tools for transforming file formats (PAGE XML) and metadata formats (METS). It is a kind of Ground Truth Swiss Knife ;-)

gt-fraktur. Shell

maskrcnn_tf2. Mask R-CNN for object detection and instance segmentation with Keras and TensorFlow V2 and ONNX and TensorRT optimization support.

geokelone. integrates spatial and textual data processing tools into a modular software package which features preprocessing, geocoding, disambiguation and visualization

page-to-alto. Convert PAGE (v. 2019) to ALTO (v. 2.0 - 4.2)

ocrd_fileformat. OCR-D wrapper for ocr-fileformat

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

bowkin. A tool for patching binaries to use specific versions of glibc

tensorflow-wheels. A repo to store custom tensorflow wheels in releases

mets-mods2tei. Convert bibliographic meta data in MODS format to TEI headers

Fibeln. Transkriptionen von Fibeln (19. Jahrhundert)

awesome-pipeline. A curated list of awesome pipeline toolkits inspired by Awesome Sysadmin

mets2iiif. An implementation of the IIIF Presentation API v2 based on XSLT

Multi-Type-TD-TSR. Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition

CTCDecoder. Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

ocr-greek_cursive. Training files for Greek cursive script (in early print)

German-NLP. Curated list of open-access/open-source/off-the-shelf resources and tools developed with a particular focus on German

timur. Finite-state morphology for German

DeslantImg. The deslanting algorithm sets text upright in images. Python, C++ and OpenCL implementations provided.

ALBEF. Code for ALBEF: a new vision-language pre-training method

cookiecutter. A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.

ocrd-gbn. OCR-D compliant toolset for optical layout recognition on historical german-language documents published in Brazil

table-transformer. Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

PyLaia. A deep learning toolkit specialized for handwritten document analysis

PrintedBookLayout.

Doxa. A Local Adaptive Thresholding framework for image binarization written in C++, with JS, Python and MATLAB bindings. Implementing: Otsu, Bernsen, Niblack, Bradley, Sauvola, Wolf, Gatos, NICK, Su, T.R. Singh, WAN, ISauvola, Feng, Phansalkar, AdOtsu, along with DRDM and all Pseudo Merics.

hist_thresh. Jupyter Notebook

dask. Parallel computing with task scheduling

warp-ctc. Fast parallel CTC.

nautilusocr. METS/ALTO OCR enhancing tool by the National Library of Luxembourg (BnL)

TextRecognitionDataGenerator. A synthetic data generator for text recognition

EasyOCR. Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

tess5train-fonts. Files and Scripts to run Tesseract 5 LSTM Training using fonts

tractjs. Run ONNX and TensorFlow inference in the browser.

wtpsplit. Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

modern-unix. A collection of modern/faster/saner alternatives to common unix commands.

solr-ocrhighlighting. Highlighting various OCR formats directly in Solr

DocCreator. DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation

Android-OTA-update-by-USB-disk. Roff

bibliothekartag-2021. Slides presenting the collaborative OCR GT collection at SLUB

neuspell. NeuSpell: A Neural Spelling Correction Toolkit

ACL2018_Multi_Input_OCR. Python

text-matcher. A simple text reuse detection CLI tool.

ocr4all_models. Pretrained mixed models to be used in OCR4all

langid.py. Stand-alone language identification system

cibuildwheel. 🎡 Build Python wheels for all the platforms with minimal configuration.

pylsd. python bindings for LSD - Line Segment Detector.

DocumentLayoutAnalysis. Document Layout Analysis resources repos for development with PdfPig.

ocr-text-extraction. A simple program to extract the text from an image before performing OCR

htr-gt. Sources for training Handwritten Text Recognition models