Advertisement

Nateq Reading Arabic Text for Visually Impaired People

  • Omaimah Bamasag
  • Muna Tayeb
  • Maha Alsaggaf
  • Fatimah Shams
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10907)

Abstract

Nateq is a system developed to aid visually impaired people in their daily life tasks. Nateq allows blind users to read text written on papers and labels using their mobile phones. It uses two sources to read text from, either from camera or photo gallery. In the camera mode, the system will automatically capture the image once the object is sufficiently detected along with an option to capture the image of the object manually. To increase the accuracy, a novel approach was implemented to ensure the correctness of the extracted text, by adding rectangular boundaries detection to the system. It helps the user to avoid partial capturing of the object which may lead to extracting incomplete sentences. Testing on target users showed high level of satisfaction on the improvement made in the field of assistive application with an overall process being faster in comparison to similar applications in the market.

Keywords

Visual impairment Image processing Text extraction Boundaries detection OCR Accessibility Reader assistant 

References

  1. 1.
    Acapela TTS. http://www.acapela-group.com/. Accessed 15 Nov 2016
  2. 2.
    Apple Inc.: General Battery Information. https://www.apple.com/sa/iphone/battery.html
  3. 3.
    Apple Inc.: CIDetector. https://developer.apple.com/reference/ coreimage/cidetector. Accessed 20 May 2017
  4. 4.
    Apple Inc.: Apple VoiceOver. http://www.apple.com/accessibility/mac/vision/. Accessed 20 Nov 2016
  5. 5.
    Blindness and Vision Impairment, 8 February 2011. http://www.cdc.gov/healthcommunication/ToolsTemplates/EntertainmentEd/Tips/Blindness.html. Accessed 10 Nov 2016
  6. 6.
    CamScanner. https://www.camscanner.com. Accessed 15 Nov 2016
  7. 7.
    Google corp. Google Translate. https://play.google.com/. Accessed 20 Nov 2016
  8. 8.
    Google Cloud Platform. cloud.google.com/vision/docs. Accessed 17 Mar 2017
  9. 9.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar
  10. 10.
    Sensotec: KNFB Reader. http://www.knfbreader.com/. Accessed 15 Nov 2016
  11. 11.
    World Health Organization: Global Data on Visual Impairments. Silvio P. Mariotti, Geneva (2010)Google Scholar
  12. 12.
    Mochizuki, Y., Mochizuki, T.: Amedia Live Reader. http://www.amedia.co.jp/english/product/iphone/livereader. Accessed 15 Nov 2016
  13. 13.
    OpenCV: OpenCV Library (2011). docs.opencv.org/2.4/doc/. Accessed 16 Mar 2017
  14. 14.
    VOXYGEN: Adel TTS. https://best-of-vox.com/android (n.d.)
  15. 15.
    Wellnitz, R.: Text Fairy (OCR Text Scanner). https://play.google.com/. Accessed 15 Nov 2016.

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Omaimah Bamasag
    • 1
  • Muna Tayeb
    • 2
  • Maha Alsaggaf
    • 2
  • Fatimah Shams
    • 2
  1. 1.Faculty of Computing and Information Technology, Computer Science DepartmentUniversity of JeddahJeddahSaudi Arabia
  2. 2.Faculty of Computing and Information Technology, Information Technology Department, Computer Science DepartmentKing Abdulaziz UniversityJeddahSaudi Arabia

Personalised recommendations