ML to categorize and translate images into tactile graphics

The amount of people who suffer from some kind of visual disability right now is staggering: 253 million people were suffering from some type of visual impairment by 2015, and this numbers aren't stopping. These are people that can't get access to an equal learning experience as child or a fair competition in the workplace. Tactile Graphics are a kind of representation of images for the blind that can leverage in some way the disadvantages these people have, by letting the blind sense the content of images through their touch. Although the technology for creating these kind of images has improved a lot, the means to find them and provide Tactile Graphics to people is very inefficient. In this paper, we present a solution to this problem, taking advantage of the knowledge we have about Tactile Graphics at the moment and using the benefits of Machine Learning to know what exactly defines a good tactile graphic

• Autores: González Álvarez, Carlos Eduardo
• Tipo de recurso: Trabajo de grado de pregrado
• Fecha de publicación: 2018
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: eng
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/38930
• Acceso en línea: http://hdl.handle.net/1992/38930
• Palabra clave: Gráficos táctiles; Personas con daño visual; Dispositivos de autoayuda para personas con discapacidades; Aprendizaje automático (Inteligencia artificial); Ingeniería
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/