A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A Unified Toolkit for Deep Learning Based Document Image Analysis

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

Read and extract text and other content from PDFs in C# (port of PDFBox)

OCR engine for all the languages

Document Layout Analysis resources repos for development with PdfPig.

Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

A toolbox of ocr models and algorithms based on MindSpore

📝 针对文档类图像做内容提取，将文档类图像一比一输出到Word或者Txt中，便于进一步使用或处理。后续计划支持输入PDF/图像，输出对应json格式、Txt格式、Word格式和Markdown格式。

Analysis of Chinese and English layouts 中英文版面分析

Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.

An official implementation of paper "Paragraph2Graph: A Language-independent GNN-based framework for layout analysis"

YOLO models trained by DocLayNet - power your Document Intelligent by Layout Analysis

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

[ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)

A Large Dataset of Historical Japanese Documents with Complex Layouts

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.

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

利用java-yolov8实现版面检测（Chinese layout detection），java-yolov8 is used to detect the layout of Chinese document images

This library builds a graph-representation of the content of PDFs. The graph is then clustered, resulting page segments are classified and returned. Tables are retrieved formatted as a CSV.