Tactiled: Towards More and Better Tactile Graphics Using Machine Learning

The TACTILED web interface with a search box containing the word 'Dog' and an Upload Your File button. Below are five silhouette images of dogs and a paw print, each labeled GREAT or FAIR to indicate suitability for tactile graphic production.
Figure 1: TACTILED interface showing example images rated as suitable or unsuitable for tactile graphic production, with quality classifications (GREAT/FAIR) below each image.
Abstract
This poster presents Tactiled, a tool that leverages machine learning to automatically generate tactile graphics from visual images. The work aims to increase accessibility for blind and low-vision users by making visual content tangible.
Materials
DOI | BibTeX
Authors
Ricardo Gonzalez
Carlos Gonzalez
John Alexis Guerra Gomez
Citation
Thumbnail image for publication titled: Tactiled: Towards More and Better Tactile Graphics Using Machine Learning
Tactiled: Towards More and Better Tactile Graphics Using Machine Learning

Ricardo Gonzalez, Carlos Gonzalez, and John Alexis Guerra-Gomez. Proc. ASSETS—ASSETS. 2019. DOI: 10.1145/3308561.3354613

DOI | BibTeX

Khoury Vis Lab — Northeastern University
* West Village H, Room 302, 440 Huntington Ave, Boston, MA 02115, USA
* 100 Fore Street, Portland, ME 04101, USA
* Carnegie Hall, 201, 5000 MacArthur Blvd, Oakland, CA 94613, USA