• DocumentCode
    2134350
  • Title

    The Research on Paper-Mediated Braille Automatic Recognition Method

  • Author

    Yin, Jia ; Wang, Lirong ; Li, Jie

  • Author_Institution
    Grad. Sch., Changchun Univ. of Sci. & Technol., Changchun, China
  • fYear
    2010
  • fDate
    18-22 Aug. 2010
  • Firstpage
    619
  • Lastpage
    624
  • Abstract
    The paper-mediated Braille automatic recognition method referred in this paper, for the scanned Braille images, pre-process the Braille images, convert into Braille binary image and then extract the Braille features by the fixed nature of Braille. Then grouping, locating, marking the Braille cells, establish a standard Braille Corpus according as one-to-one Correspondence between Braille cell and character contains Hanyu Pinyin, Arabic numerals and interpunction, then match the recognized Braille cells and finally output the sentences formed Hanyu Pinyin, Arabic numerals and interpunation. This method is simple convenient, and easy to operate. The paper introduces Braille extraction, Braille recognition, illuminates specific experimental approach in details. Experiments show that the method can effectively extract Braille, and accurately convert the Braille into Hanyu Pinyin.
  • Keywords
    feature extraction; handicapped aids; image recognition; image segmentation; optical character recognition; Arabic numerals; Braille Corpus; Braille binary image; Braille cell; Braille character; Braille recognition; Hanyu Pinyin numerals; feature extraction; interpunction; paper-mediated Braille automatic recognition method; scanned Braille images; Arrays; Character recognition; Feature extraction; Histograms; Image recognition; Image segmentation; Braille Image Enhancement; Braille Image Segmentation; Braille Recognition; Braille dots feature extraction;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Frontier of Computer Science and Technology (FCST), 2010 Fifth International Conference on
  • Conference_Location
    Changchun, Jilin Province
  • Print_ISBN
    978-1-4244-7779-1
  • Type

    conf

  • DOI
    10.1109/FCST.2010.95
  • Filename
    5575584