OCR, layout analysis, reading order, table recognition in 90+ languages

Convert PDF to markdown + JSON quickly with high accuracy

A linux driver for the mt9m114 camera chip.

Tools to build Microsoft Windows screensavers which are Linux distributions

Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.

Try to find regions missed by Tesseract.

Web interface for recognizing text, proofreading OCR, and creating fully-digitized documents.

Automatically exported from code.google.com/p/decapod

Fork of https://bitbucket.org/mrudolf/djview-poliqarp/

Differentiable Vector Graphics Rasterization

[AAAI 2024] SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression

Access, upload, download, and do much more with OneDrive using Microsoft Graph API (Python code).

CRAFT-Pyotorch：Character Region Awareness for Text Detection Reimplementation for Pytorch

CRAFT算法的训练

PyTorch Re-Implementation of CRAFT: Character Region Awareness for Text Detection

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Text detection with mainly MSER and SWT

CentOS 6.9 build Docker environment to distribute portable Linux binaries

Document binarization using deep learning

Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture (accepted by PVLDB)

[SIGGRAPH Asia 2021] DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning

Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver

Accelerate PyTorch models with ONNX Runtime

docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

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

A curated list of resources for Document Understanding (DU) topic

Tensors and Dynamic neural networks in Python with strong GPU acceleration