Vision Accessibility Data Initiative

The visual accessibility of a space refers to the effectiveness with which vision can be used to travel safely and pursue intended activities in the space. Visual accessibility of a space is lower for impaired vision, leading to higher risks of encountering hazardous situations, falling, and being disoriented in navigation.

Environmental accessibility can be improved by enhancing the visibility of informative or hazardous features through cost-effective modifications of contrast, illumination, and materials. However, it is difficult for people with normal vision, even those with rehab expertise, to judge whether specific objects or features would be visible for individuals with different levels of vision impairment, or to judge the efficacy of modifications. While there is clear guidelines and regulations for enhancing the physical accessibility of spaces, the evaluation of visual accessibility lacks an objective system.

We initiate the Visual Accessibility Data Initiative to bring data-driven and human-centered approaches into developing objective systems for evaluating and enhancing the visual accessibilities of informative and hazardous features in our environments.

news

Aug 16, 2024	Congratulations to our team for officially receiving a NIH R01 grant for the visual accessibility project!
May 18, 2024	Yingzi gave a talk on “Enhancing visual environmental accessibility ”at the VSS DEI workshop.
May 05, 2024	Qingying gave a poster on “Creating A “Visually Impaired” Character Recognition Model for Text Accessibility Assessment” at ARVO 2024.

selected publications

ARVO
Creating A “Visually Impaired” Character Recognition Model for Text Accessibility Assessment

Qingying Gao, Roberto Manduchi, Pradeep Y Ramulu, and 2 more authors

Investigative Ophthalmology & Visual Science, 2024

Abs Bib

Low vision individuals use their residual vision in their daily life to read text such as price tags, street signs, medicine labels. However, there is no objective tool for evaluating text accessibility for low vision. As modern Optical Character Recognition (OCR) achieves high performance in text recognition, it may be possible to develop “visually impaired” OCR (VI-OCR) to mimic low vision performance and serve as a tool for assessing text visibility. We aim to design a new framework combining OCR and human contrast sensitivity functions (CSF) to simulate the text recognition capability of low vision.
@article{gao2024creating, title = {Creating A “Visually Impaired” Character Recognition Model for Text Accessibility Assessment}, author = {Gao, Qingying and Manduchi, Roberto and Ramulu, Pradeep Y and Legge, Gordon E and Xiong, Yingzi}, journal = {Investigative Ophthalmology \& Visual Science}, volume = {65}, number = {7}, pages = {1118--1118}, year = {2024}, publisher = {The Association for Research in Vision and Ophthalmology}, }

Journal

Simulating visibility and reading performance in low vision

Ying-Zi Xiong, Quan Lei, Aurlie Calabrse, and 1 more author

Frontiers in Neuroscience, 2021

Bib

@article{xiong2021simulating,
  title = {Simulating visibility and reading performance in low vision},
  author = {Xiong, Ying-Zi and Lei, Quan and Calabrse, Aurlie and Legge, Gordon E},
  journal = {Frontiers in Neuroscience},
  volume = {15},
  pages = {671121},
  year = {2021},
  publisher = {Frontiers Media SA},
}

Journal

Fonts designed for macular degeneration: Impact on reading

Ying-Zi Xiong, Ethan A Lorsung, John Stephen Mansfield, and 2 more authors

Investigative ophthalmology & visual science, 2018

Bib

@article{xiong2018fonts,
  title = {Fonts designed for macular degeneration: Impact on reading},
  author = {Xiong, Ying-Zi and Lorsung, Ethan A and Mansfield, John Stephen and Bigelow, Charles and Legge, Gordon E},
  journal = {Investigative ophthalmology \& visual science},
  volume = {59},
  number = {10},
  pages = {4182--4189},
  year = {2018},
  publisher = {The Association for Research in Vision and Ophthalmology},
}