ihdia / docvisor
An open-source tool for visualisation of outputs of deep-learning models for document analysis tasks such as fully automatic, bounding box and OCR.
☆19Updated 2 years ago
Related projects: ⓘ
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 2 years ago
- A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers☆52Updated last week
- ☆74Updated last year
- [ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)☆36Updated 11 months ago
- Official repository accompaying the ICDAR 2023 paper☆10Updated 11 months ago
- [ICDAR 2023] (Oral) An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation☆69Updated last week
- Line Chart Data Extraction: Official code for LineFormer - ICDAR23 Paper☆23Updated 3 months ago
- Easter2.0: IMPROVING CONVOLUTIONAL MODELS FOR HANDWRITTEN TEXT RECOGNITION☆75Updated last year
- Hadwritten Text Recognition in Few-shot Scenario☆18Updated last year
- Handwritten text recognition using transformers.☆147Updated last month
- CVPR 2022: Table Structure Recognition☆39Updated 2 years ago
- Code for BMVC2020 paper "Text and Style Conditioned GAN for Generation of Offline Handwriting Lines"☆66Updated last year
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆69Updated 3 years ago
- Detect textlines in document images☆88Updated 3 months ago
- Official implementation for Dessurt☆56Updated last year
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆113Updated last year
- ☆71Updated last year
- PyTorch implementation of STR models for transfer learning in Indic Languages☆15Updated 3 years ago
- ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation☆120Updated 2 months ago
- Pytorch implementation of our paper: Adapting OCR with Limited Labels☆56Updated 8 months ago
- Form images from U.S. National Archives annotated with text bounding boxes, classes, relationships, and transcription.☆34Updated 2 years ago
- OCR Annotations from Amazon Textract for Industry Documents Library☆99Updated 2 years ago
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆253Updated last year
- DocILE: Document Information Localization and Extraction Benchmark☆116Updated 4 months ago
- DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis☆235Updated last year
- Attention-based sequence-to-sequence model for handwritten word recognition☆55Updated last year
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆121Updated 10 months ago
- Repository for the deep-learning framework DIVA-DAF which is build with historical document image analysis in mind.☆18Updated last month
- Repo to host the forms dataset☆13Updated 3 years ago
- ☆18Updated 2 years ago