Scatteract: Automated Extraction of Data from Scatter Plots
Abstract
Charts are an excellent way to convey patterns and trends in data, but they do not facilitate further modeling of the data or close inspection of individual data points. We present a fully automated system for extracting the numerical values of data points from images of scatter plots. We use deep learning techniques to identify the key components of the chart, and optical character recognition together with robust regression to map from pixels to the coordinate system of the chart. We focus on scatter plots with linear scales, which already have several interesting challenges. Previous work has done fully automatic extraction for other types of charts, but to our knowledge this is the first approach that is fully automatic for scatter plots. Our method performs well, achieving successful data extraction on 89% of the plots in our test set.
Cite
Text
Cliche et al. "Scatteract: Automated Extraction of Data from Scatter Plots." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017. doi:10.1007/978-3-319-71249-9_9Markdown
[Cliche et al. "Scatteract: Automated Extraction of Data from Scatter Plots." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017.](https://mlanthology.org/ecmlpkdd/2017/cliche2017ecmlpkdd-scatteract/) doi:10.1007/978-3-319-71249-9_9BibTeX
@inproceedings{cliche2017ecmlpkdd-scatteract,
title = {{Scatteract: Automated Extraction of Data from Scatter Plots}},
author = {Cliche, Mathieu and Rosenberg, David S. and Madeka, Dhruv and Yee, Connie},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2017},
pages = {135-150},
doi = {10.1007/978-3-319-71249-9_9},
url = {https://mlanthology.org/ecmlpkdd/2017/cliche2017ecmlpkdd-scatteract/}
}