Visualizing for the non-visual: Enabling the visually impaired to use visualization

Jinho Choi, Sanghun Jung, Deok Gun Park, Jaegul Choo, Niklas Elmqvist

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The majority of visualizations on the web are still stored as raster images, making them inaccessible to visually impaired users. We propose a deep-neural-network-based approach that automatically recognizes key elements in a visualization, including a visualization type, graphical elements, labels, legends, and most importantly, the original data conveyed in the visualization. We leverage such extracted information to provide visually impaired people with the reading of the extracted information. Based on interviews with visually impaired users, we built a Google Chrome extension designed to work with screen reader software to automatically decode charts on a webpage using our pipeline. We compared the performance of the back-end algorithm with existing methods and evaluated the utility using qualitative feedback from visually impaired users.

Original languageEnglish
Pages (from-to)249-260
Number of pages12
JournalComputer Graphics Forum
Volume38
Issue number3
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Visualization
Labels
Pipelines
Feedback

Keywords

  • Human-centered computing → Visual analytics
  • Visualization toolkits

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

Visualizing for the non-visual : Enabling the visually impaired to use visualization. / Choi, Jinho; Jung, Sanghun; Park, Deok Gun; Choo, Jaegul; Elmqvist, Niklas.

In: Computer Graphics Forum, Vol. 38, No. 3, 01.01.2019, p. 249-260.

Research output: Contribution to journalArticle

Choi, Jinho ; Jung, Sanghun ; Park, Deok Gun ; Choo, Jaegul ; Elmqvist, Niklas. / Visualizing for the non-visual : Enabling the visually impaired to use visualization. In: Computer Graphics Forum. 2019 ; Vol. 38, No. 3. pp. 249-260.
@article{087ef262864c46669c50661e4ed4232b,
title = "Visualizing for the non-visual: Enabling the visually impaired to use visualization",
abstract = "The majority of visualizations on the web are still stored as raster images, making them inaccessible to visually impaired users. We propose a deep-neural-network-based approach that automatically recognizes key elements in a visualization, including a visualization type, graphical elements, labels, legends, and most importantly, the original data conveyed in the visualization. We leverage such extracted information to provide visually impaired people with the reading of the extracted information. Based on interviews with visually impaired users, we built a Google Chrome extension designed to work with screen reader software to automatically decode charts on a webpage using our pipeline. We compared the performance of the back-end algorithm with existing methods and evaluated the utility using qualitative feedback from visually impaired users.",
keywords = "Human-centered computing → Visual analytics, Visualization toolkits",
author = "Jinho Choi and Sanghun Jung and Park, {Deok Gun} and Jaegul Choo and Niklas Elmqvist",
year = "2019",
month = "1",
day = "1",
doi = "10.1111/cgf.13686",
language = "English",
volume = "38",
pages = "249--260",
journal = "Computer Graphics Forum",
issn = "0167-7055",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Visualizing for the non-visual

T2 - Enabling the visually impaired to use visualization

AU - Choi, Jinho

AU - Jung, Sanghun

AU - Park, Deok Gun

AU - Choo, Jaegul

AU - Elmqvist, Niklas

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The majority of visualizations on the web are still stored as raster images, making them inaccessible to visually impaired users. We propose a deep-neural-network-based approach that automatically recognizes key elements in a visualization, including a visualization type, graphical elements, labels, legends, and most importantly, the original data conveyed in the visualization. We leverage such extracted information to provide visually impaired people with the reading of the extracted information. Based on interviews with visually impaired users, we built a Google Chrome extension designed to work with screen reader software to automatically decode charts on a webpage using our pipeline. We compared the performance of the back-end algorithm with existing methods and evaluated the utility using qualitative feedback from visually impaired users.

AB - The majority of visualizations on the web are still stored as raster images, making them inaccessible to visually impaired users. We propose a deep-neural-network-based approach that automatically recognizes key elements in a visualization, including a visualization type, graphical elements, labels, legends, and most importantly, the original data conveyed in the visualization. We leverage such extracted information to provide visually impaired people with the reading of the extracted information. Based on interviews with visually impaired users, we built a Google Chrome extension designed to work with screen reader software to automatically decode charts on a webpage using our pipeline. We compared the performance of the back-end algorithm with existing methods and evaluated the utility using qualitative feedback from visually impaired users.

KW - Human-centered computing → Visual analytics

KW - Visualization toolkits

UR - http://www.scopus.com/inward/record.url?scp=85070078390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070078390&partnerID=8YFLogxK

U2 - 10.1111/cgf.13686

DO - 10.1111/cgf.13686

M3 - Article

AN - SCOPUS:85070078390

VL - 38

SP - 249

EP - 260

JO - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 0167-7055

IS - 3

ER -