# Scatteract: Automated extraction of data from scatter plots

arXiv: https://arxiv.org/abs/1704.06687 · HTML: https://mlsanity.com/paper/1704.06687/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2017.

## Built on by (most cited first, 11 of 11)

- [AutoChart: A Dataset for Chart-to-Text Generation Task](https://mlsanity.com/paper/2108.06897/) (2021)
- [Towards an efficient framework for Data Extraction from Chart Images](https://mlsanity.com/paper/2105.02039/) (2021)
- [START: Spatial and Textual Learning for Chart Understanding](https://mlsanity.com/paper/2512.07186/) (2025)
- [CHARTER: heatmap-based multi-type chart data extraction](https://mlsanity.com/paper/2111.14103/) (2021)
- [VizExtract: Automatic Relation Extraction from Data Visualizations](https://mlsanity.com/paper/2112.03485/) (2021)
- [Interpreting Audiograms with Multi-stage Neural Networks](https://mlsanity.com/paper/2112.09357/) (2021)
- [An extensible point-based method for data chart value detection](https://mlsanity.com/paper/2308.11788/) (2023)
- [Dual Reinforcement-Based Specification Generation for Image De-Rendering](https://mlsanity.com/paper/2103.01867/) (2021)
- [OsmLocator: locating overlapping scatter marks with a non-training generative perspective](https://mlsanity.com/paper/2312.11146/) (2023)
- [Reconstructing High-Dimensional Datasets From Their Bivariate Projections](https://mlsanity.com/paper/2312.15306/) (2023)
- [Kyrtos: A methodology for automatic deep analysis of graphic charts with curves in technical documents](https://mlsanity.com/paper/2602.09337/) (2026)

## Abstract (arXiv)

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.