Reverse-Engineering Visualizations: Recovering Visual Encodings from Chart Images

Simple item page
dc.contributor.authorPoco, Jorgeen_US
dc.contributor.authorHeer, Jeffreyen_US
dc.contributor.editorHeer, Jeffrey and Ropinski, Timo and van Wijk, Jarkeen_US
dc.date.accessioned2017-06-12T05:22:50Z
dc.date.available2017-06-12T05:22:50Z
dc.date.issued2017
dc.description.abstractWe investigate how to automatically recover visual encodings from a chart image, primarily using inferred text elements. We contribute an end-to-end pipeline which takes a bitmap image as input and returns a visual encoding specification as output. We present a text analysis pipeline which detects text elements in a chart, classifies their role (e.g., chart title, x-axis label, y-axis title, etc.), and recovers the text content using optical character recognition. We also train a Convolutional Neural Network for mark type classification. Using the identified text elements and graphical mark type, we can then infer the encoding specification of an input chart image. We evaluate our techniques on three chart corpora: a set of automatically labeled charts generated using Vega, charts from the Quartz news website, and charts extracted from academic papers. We demonstrate accurate automatic inference of text elements, mark types, and chart specifications across a variety of input chart types.en_US
dc.description.number3
dc.description.sectionheadersVisual Encoding Analysis
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.13193
dc.identifier.issn1467-8659
dc.identifier.pages353-363
dc.identifier.urihttps://doi.org/10.1111/cgf.13193
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13193
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleReverse-Engineering Visualizations: Recovering Visual Encodings from Chart Imagesen_US
Files
Collections
36-Issue 3