A Unified Toolkit for Deep Learning Based Document Image Analysis

A Repo For Document AI

基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.

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

📚 Process PDFs, Word documents and more with spaCy

Document Layout Analysis resources repos for development with PdfPig.

Document Layout Analysis

Page to PAGE Layout Analysis Tool

Detectron2 for Document Layout Analysis

ICDAR 2019: MaskRCNN on PubLayNet datasets. Paragraph detection, table detection, figure detection,...

Complex data extraction and orchestration framework designed for processing unstructured documents. It integrates AI-powered document pipelines (GenAI, LLM, VLLM) into your applications, supporting various tasks such as document cleanup, optical character recognition (OCR), classification, splitting, named entity recognition, and form processing

A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers

Trained Detectron2 object detection models for document layout analysis based on PubLayNet dataset

Tools for extract figure, table, text, .. from a pdf document.

Trained Detectron2 object detection models for document layout analysis based on PubLayNet dataset

Proof of concept of training a simple Region Classifier using PdfPig and ML.NET (LightGBM). The objective is to classify each text block in a pdf document page as either title, text, list, table and image.

A step-by-step C# implementation of the Docstrum algorithm

BoundaryNet - A Semi-Automatic Layout Annotation Tool

Simple docker deployment of document layout analysis using detectron2

Using a MaskRCNN model trained on the PublayNet dataset with ML.Net in C# / .Net for Document layout analysis and page segmmentation task.