sparkfish / augraphy
Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes
☆407Updated 3 weeks ago
Alternatives and similar repositories for augraphy:
Users that are interested in augraphy are comparing it to the libraries listed below
- Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021☆514Updated 10 months ago
- ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation☆134Updated 3 months ago
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks☆184Updated last year
- ☆159Updated 2 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆125Updated 11 months ago
- Distorted Document Images dataset (DDI-100).☆136Updated 2 years ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆187Updated last month
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆271Updated 2 years ago
- Document Dewarping with Control Points☆171Updated 2 years ago
- PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)☆302Updated last year
- A collection of OCR-related datasets☆161Updated 2 years ago
- Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector☆263Updated 2 years ago
- Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labelin…☆256Updated 9 months ago
- Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understan…☆346Updated 2 years ago
- Papers, Datasets, Algorithms, SOTA for STR. Long-time Maintaining☆343Updated last year
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆140Updated last year
- Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation☆191Updated last year
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆80Updated 2 years ago
- document image degradation☆163Updated 4 years ago
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…☆322Updated last year
- CRAFT(Baek et al., 2019) model training code☆46Updated 8 months ago
- Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)☆634Updated 10 months ago
- DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation☆120Updated last year
- This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadowing, …☆238Updated 2 months ago
- ☆81Updated last year
- The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and p…☆282Updated 4 months ago
- A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".☆478Updated 3 years ago
- Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition☆445Updated 2 years ago
- Detectron2 for Document Layout Analysis☆187Updated 8 months ago
- A hybrid dataset for document unwarping (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)☆170Updated 2 years ago