Cvrane/ChartReader
Fully automated end-to-end framework to extract data from bar plots and other figures in scientific research papers using modules such as OpenCV, AWS-Rekognition.
This tool helps researchers, scientists, and data analysts extract numerical data from various types of charts and figures found in scientific papers. It takes images of bar plots, line graphs, and other common visualizations as input and outputs the underlying data points, axes labels, and legend information. This is ideal for anyone needing to digitize graphical data for further analysis or replication.
128 stars. No commits in the last 6 months.
Use this if you frequently need to get precise numerical values from bar plots, line graphs, or scatter plots presented in scientific publications without manually estimating them.
Not ideal if you primarily work with complex or highly stylized diagrams that are not standard chart types, or if you need to extract information from tables, as this focuses on visual charts.
Stars
128
Forks
22
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 15, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Cvrane/ChartReader"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
Psarpei/Multi-Type-TD-TSR
Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and...
Layout-Parser/layout-parser
A Unified Toolkit for Deep Learning Based Document Image Analysis
Sudhanshu1304/table-transformer
🔍 Table Extraction Tool: A powerful open-source solution combining OCR and computer vision for...
ses4255/Versatile-OCR-Program
Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)
asagar60/TableNet-pytorch
Pytorch Implementation of TableNet