Table Extraction OCR ML Frameworks

Tools for detecting, extracting, and recognizing tables from document images using computer vision and OCR techniques. Does NOT include general document processing, chart/figure extraction, or standalone OCR for unstructured text.

There are 23 table extraction ocr frameworks tracked. The highest-rated is Layout-Parser/layout-parser at 46/100 with 5,678 stars.

Get all 23 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=table-extraction-ocr&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	Layout-Parser/layout-parser A Unified Toolkit for Deep Learning Based Document Image Analysis	46	Emerging	5,678	Python
2	Psarpei/Multi-Type-TD-TSR Extracting Tables from Document Images using a Multi-stage Pipeline for...	40	Emerging	282	Jupyter Notebook
3	ses4255/Versatile-OCR-Program Multi-modal OCR pipeline optimized for ML training (text, figure, math,...	37	Emerging	682	Python
4	Sudhanshu1304/table-transformer 🔍 Table Extraction Tool: A powerful open-source solution combining OCR and...	37	Emerging	93	Python
5	asagar60/TableNet-pytorch Pytorch Implementation of TableNet	37	Emerging	66	Jupyter Notebook
6	JG1VPP/MuTabNet ICDAR 2024 Table OCR Model	36	Emerging	39	Python
7	VikParuchuri/tabled Detect and extract tables to markdown and csv	35	Emerging	755	Python
8	MrZilinXiao/Hyper-Table-OCR A carefully-designed OCR pipeline for universal boarded table recognition...	32	Emerging	178	C++
9	Cvrane/ChartReader Fully automated end-to-end framework to extract data from bar plots and...	29	Experimental	128	Jupyter Notebook
10	MasterAI-EAM/GraphMaster Fully automated end to end framework to extract data from complex charts and...	27	Experimental	19	Jupyter Notebook
11	abdoelsayed2016/TNCR_Dataset Deep learning, Convolutional neural networks, Image processing, Document...	25	Experimental	69	Python
12	muhd-umer/pyramidtabnet Official PyTorch implementation of PyramidTabNet: Transformer-based Table...	23	Experimental	28	Python
13	Kaisanya/NanoTabVLM 📊 Transform images of tables into accurate HTML text with NanoTabVLM, a...	22	Experimental	—	Python
14	CaseDrive/publaynet-models Trained Detectron2 object detection models for document layout analysis...	22	Experimental	29	Python
15	AshishSalaskar1/TableNet_Implementation Extract Tabular data from scanned document images and save the tabular data...	21	Experimental	9	Jupyter Notebook
16	stuartemiddleton/glosat_table_dataset GloSAT Historical Measurement Table Dataset	20	Experimental	11	Python
17	SAP-samples/clustertabnet Implementation of the table detection and table structure recognition deep...	20	Experimental	14	Jupyter Notebook
18	FutureRising007/Table_Structure_Recognition Table Structure Recognition	17	Experimental	82	—
19	Wa1den-jy/Topic-on-Table-Recognition This is a survey on the topic of table recognition	14	Experimental	9	—
20	shahin-ro/Table-Detection Python tool for table extraction & Persian OCR. Uses OpenCV for table...	14	Experimental	3	Jupyter Notebook
21	kanhao100/IndustrialDigitDatasetGenerator A tool for generating number image datasets in industrial scenarios.	13	Experimental	5	Python
22	NeelDevenShah/Document-Layout-Analysis-for-Figure-Localization-in-Technical-PDFs This repository provides three state-of-the-art models fine-tuned on the...	13	Experimental	2	Jupyter Notebook
23	Gwinke/TIDE-4-Bachelor-Project-2025 TIDE-4: An End-to-End Pipeline for Scientific Table Extraction in...	11	Experimental	—	Jupyter Notebook

Comparisons in this category

TableNet-pytorch and pyramidtabnet (37 vs 23)