microsoft / genalogLinks
Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.
☆325Updated last year
Alternatives and similar repositories for genalog
Users that are interested in genalog are comparing it to the libraries listed below
Sorting:
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks☆185Updated last year
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆276Updated 2 years ago
- ☆160Updated 2 years ago
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 3 years ago
- Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021☆527Updated 11 months ago
- ☆80Updated last year
- Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes☆417Updated 2 months ago
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆81Updated 3 years ago
- Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understan…☆349Updated 2 years ago
- DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation☆119Updated last year
- Distorted Document Images dataset (DDI-100).☆137Updated 2 years ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆143Updated 3 weeks ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆191Updated 3 months ago
- Detectron2 for Document Layout Analysis☆187Updated 10 months ago
- DocILE: Document Information Localization and Extraction Benchmark☆127Updated last year
- Publicly released code for the LAMBERT model☆103Updated 3 years ago
- ☆246Updated 2 years ago
- CORD: A Consolidated Receipt Dataset for Post-OCR Parsing☆424Updated 2 years ago
- Code for my ICDAR paper "Deep Visual Template-Free Form Parsing"☆88Updated 3 years ago
- document image degradation☆163Updated 5 years ago
- ICDAR 2019: MaskRCNN on PubLayNet datasets. Paragraph detection, table detection, figure detection,...☆180Updated 4 years ago
- CVPR 2022: Table Structure Recognition☆39Updated 3 years ago
- CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images☆133Updated 4 months ago
- Experimental form data extraction for journalism☆77Updated 4 years ago
- ☆127Updated 5 years ago
- The scripts for training Detectron2-based Layout Models on popular layout analysis datasets☆211Updated last year
- ☆130Updated 2 years ago
- Form images from U.S. National Archives annotated with text bounding boxes, classes, relationships, and transcription.☆38Updated 3 years ago
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆122Updated 2 years ago
- Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition:☆276Updated 2 years ago