Visualization designers regularly use color to encode quantitative or categorical data. However, visualizations "in the wild" often violate perceptual color design principles and may only be available as bitmap images. In this work, we contribute a method to semi-automatically extract color encodings from a bitmap visualization image. Given an image and a legend location, we classify the legend as describing either a discrete or continuous color encoding, identify the colors used, and extract legend text using OCR methods. We then combine this information to recover the specific color mapping. Users can also correct interpretation errors using an annotation interface. We evaluate our techniques using a corpus of images extracted from scientific papers and demonstrate accurate automatic inference of color mappings across a variety of chart types. In addition, we present two applications of our method: automatic recoloring to improve perceptual effectiveness, and interactive overlays to enable improved reading of static visualizations.

Jorge Poco is an assistant professor in the Research and Innovation Center in Computer Science (RICS) at the San Pablo Catholic University (UCSP). Previously, he was a research associate in the UW Interactive Data Lab (IDL) at the University of Washington working with Jeffrey Heer. He obtained his PhD from the NYU Polytechnic School of Engineering in 2015 under the supervision of Claudio Silva. Before going to NYU he spent a year in the Scientific Computing and Imaging Institute (SCI) at the University of Utah (UoU). He has a M.S. in Computer Science from the Instituto de Ciências Matemáticas e de Computação (ICMC) at the University of São Paulo (USP), Brasil-2010, and a B.E. in System Engineering from the National University of San Agustin (UNSA), Peru-2008.
His professional experience includes a period in zAgile Inc as a software engineer on 2008, and internships at Google Inc. (2008 and 2010), Kitware Inc (2011), Oak Ridge National Laboratory (2012) and Xerox Research(2013).

His research is focused on data visualization. He have participated in projects on information visualization, scientific visualization, and visual analytics, and was also involved in interdisciplinary collaborations that focused on the development of novel visualization methods to enable both climate and urban data analysis.