microsoft / genalog
Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.
☆309Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for genalog
- ☆155Updated last year
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆258Updated last year
- Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understan…☆345Updated 2 years ago
- ☆242Updated last year
- Detectron2 for Document Layout Analysis☆185Updated 3 months ago
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks☆184Updated last year
- The scripts for training Detectron2-based Layout Models on popular layout analysis datasets☆203Updated last year
- Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes☆355Updated 2 months ago
- document image degradation☆160Updated 4 years ago
- Distorted Document Images dataset (DDI-100).☆130Updated 2 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆118Updated 6 months ago
- ☆81Updated last year
- Publicly released code for the LAMBERT model☆102Updated 3 years ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆164Updated this week
- CVPR 2022: Table Structure Recognition☆39Updated 2 years ago
- ICDAR 2019: MaskRCNN on PubLayNet datasets. Paragraph detection, table detection, figure detection,...☆177Updated 3 years ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆129Updated last year
- Handwritten text recognition using transformers.☆154Updated 3 months ago
- DocBank: A Benchmark Dataset for Document Layout Analysis☆583Updated 3 months ago
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 2 years ago
- ☆74Updated 2 years ago
- DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis☆274Updated last year
- ☆127Updated 4 years ago
- CORD: A Consolidated Receipt Dataset for Post-OCR Parsing☆400Updated 2 years ago
- Pytorch implementation of Paper by Google Research - Representation Learning for Information Extraction from Form-like Documents.☆102Updated last year
- TableNet Implementation on Pytorch☆144Updated last year
- Software that makes labeling PDFs easy.☆391Updated 6 months ago
- Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021☆492Updated 5 months ago
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆71Updated 3 years ago
- Research papers and code on information extraction from image/pdf☆96Updated last year