A Repo For Document AI

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

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

A Python library for extracting tables from PDF documents using computer vision and image processing techniques. It converts PDF pages to images, detects tables, recognizes their structure, and outputs clean data in JSON format.

CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

Python tool for table extraction & Persian OCR. Uses OpenCV for table detection, Tesseract for text extraction, & Pandas for data output. Visualizes cells & text. Ideal for Persian documents! 📄✨

🚀 Intelligent document analysis and LaTeX conversion automation tool. Converts Word documents (.docx) to LaTeX with automatic table detection, equation recognition, and multi-format support (ACM, IEEE, Springer). Built with React & TypeScript.

[ACL 2025 🔥] A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

Docker implementation of the Tabled OCR

GloSAT Historical Measurement Table Dataset

使用opencv部署yolo11表格检测，它是百度网盘AI大赛-表格检测的第2名方案，方案里包含表格框检测，表格角点检测，表格方向分类，一共三个模块。我依然是编写了C++和Python两个版本的程序

检测和提取各种场景图片中的表格区域，并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation issues.

A Python package that converts table images into HTML format using Object Detection model and OCR.

Improved file parsing for LLM’s

Official PyTorch implementation of PyramidTabNet: Transformer-based Table Recognition in Image-based Documents

In this we extract tables from the pdf using fitz and pymudf

A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.

Table detection (TD) and table structure recognition (TSR) using Yolov5/Yolov8, and you can get the same (even better) result compared with Table Transformer (TATR) with smaller models.

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

Build a RAG preprocessing pipeline