layout-detection 开源项目推荐（18 个）

PaddlePaddle /PaddleX

基于 PaddlePaddle 的一体化开发工具

Layout-Parser /layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis

vorojar /Folio-OCR

开源批处理OCR工作台——ABBYY FineReader的免费本地替代方案。由 Ollama + GLM-OCR + PP-DocLayoutV3 驱动，RTX 4090 上每页 ~0.5 秒。三面板编辑器，布局感知，PDF/图像批量处理，Markdown/Word导出。批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。

mbzuai-oryx /KITAB-Bench

[ACL 2025] 面向阿拉伯语 OCR 与文档理解的综合多领域基准

gridaco /ui-dataset

A pre labelled dataset for ui element / layout detection

sparkfish /shabby-pages

ShabbyPages is a state-of-the-art corpus of born-digital document images with both ground truth and distorted versions appropriate for use in training models to reverse distortions and recover to original denoised documents.

jiangnanboy /layout_analysis

中文版面检测（Chinese layout detection），yolov8 is used to detect the layout of Chinese document images。

jiangnanboy /AutoText

智能文本自动处理工具（Intelligent text automatic processing tool）。AutoText的功能主要有文本纠错，图片ocr、版面检测以及表格结构识别等。The main functions of this project include text error correction, ocr, layout-detection and table structure recognition.

PT-Perkasa-Pilar-Utama /ppu-doclayout

A lightweight, type-safe, PaddlePaddle PP-DocLayoutV3 & V2 implementation in Bun/Node.js for document layout analysis in JavaScript environments.

DCC-BS /docling-pp-doc-layout

Docling plugin to integrate PP-DocLayout-V3 model into docling to enhance layout detection capabilities

pleb631 /pdfLayoutDet

pdfDet aims to simplify PDF layout detect tasks for users.

NanoNets /llm-data-converter

Convert any document format into LLM-ready data format (markdown) with advanced intelligent document processing capabilities powered by pre-trained models.

jiangnanboy /layout_detection

利用c++加载yolov8模型，进行版面检测。yolov8-c++ is used to detect the layout of Chinese document images

charlie6echo /VBDLDSCC

Vision Based Document Layout Detection, Segmentation and context classification using MaskRCNN on Tensorflow-Keras, PyTorch & Detectron2.

abhilashpanda04 /layout_parser

Document layout analysis tool for extracting structured information from documents using computer vision

hnextits /NextitsLM_DataPreProcessing

OCR, STT

ozefe /ytcc-pipeline

A synchronous Python library that converts an academic-thesis PDF into a structured JSON document plus a tar bundle of cropped figures, tables, and formulas.

tagay1n /ocr-benchmark-pipeline

Language-agnostic OCR benchmark pipeline to discover document images, review/edit layouts in a web UI, run OCR extraction, and build high-quality evaluation datasets.