Text-to-speech reading assistant device with scene text locator for the blind

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)


One of the most anticipated devices for the blind is probably a wearable camera capable of translating the captured scene text into an alternative representation such as speech. However, finding signboards and capturing the text images in a form suitable for character recognition is difficult for the blind. We propose a framework of reading assistant device with a scene text locator that shows the text location by sound signals. By using a pair of base/offset notes, the accuracy of text localization has become much higher compared with our previous system.

Original languageEnglish
Title of host publicationAssistive Technology
Subtitle of host publicationFrom Research to Practice
EditorsPedro Encarnacao, Luis Azevedo, Gert Jan Gelderblom, Alan Newell, Niels-Erik Mathiassen
Number of pages6
Publication statusPublished - 2013

Publication series

NameAssistive Technology Research Series
ISSN (Print)1383-813X
ISSN (Electronic)1879-8071


  • OCR (Optical Character Recognition)
  • Reading assistant
  • Scene text detection
  • Text locator
  • Text-to-speech


Dive into the research topics of 'Text-to-speech reading assistant device with scene text locator for the blind'. Together they form a unique fingerprint.

Cite this