DOI QR코드

DOI QR Code

시각장애인을 위한 CNN 기반의 점자 변환 및 음성 출력 장치 설계

Design of CNN-based Braille Conversion and Voice Output Device for the Blind

  • 박승빈 (서원대학교 정보통신공학과) ;
  • 김봉현 (서원대학교 컴퓨터공학과)
  • Seung-Bin Park (Department of Information Communication Engineering, Seowon University) ;
  • Bong-Hyun Kim (Department of Computer Engineering, Seowon University)
  • 투고 : 2023.04.05
  • 심사 : 2023.05.30
  • 발행 : 2023.06.30

초록

시대가 발전함에 따라 정보가 다양해지고 이를 얻는 방법도 다양해진다. 살아가면서 얻는 정보의 양 중 약 80%는 시각적 감각으로 습득한다. 하지만 시각장애인들은 시각 자료를 해석하는 능력이 제한된다. 그래서 점자라는 시각장애인용 문자가 등장했다. 그러나 시각장애인들의 점자 해독률은 5%에 불과하며 시간에 지남에 따라 다양한 형태의 플랫폼이나 자료를 원하는 시각장애인들의 요구가 늘어나면서 시각장애인들을 위한 개발 및 물품 제작이 이루어지고 있다. 물품 제작의 예로는 점자 도서를 들 수 있는데 이 점자 도서는 장점보단 단점이 많아 보이고 비장애인과 다르게 아직도 정보 접근에 대해서는 많이 어려운 것이 사실이다. 본 논문에서는 시각장애인이 정보를 기존의 방법보다 쉽게 얻을 수 있도록 CNN 기반 점자 변환 및 음성 출력 장치를 설계하였다. 이 장치는 점자로 되어 있지 않고 점자로 제작이 되지 않은 책, 텍스트 이미지나 손글씨 이미지 등을 카메라 인식을 통해 점자로 변환할 수 있도록 하고, 점자로 변환 후 시각장애인들의 요구에 따라서 음성으로 변환해 출력할 수 있는 기능을 설계해 시각장애인들이 정보를 얻을 수 있게 도와주어 삶의 질을 높이고자 한다.

As times develop, information becomes more diverse and methods of obtaining it become more diverse. About 80% of the amount of information gained in life is acquired through the visual sense. However, visually impaired people have limited ability to interpret visual materials. That's why Braille, a text for the blind, appeared. However, the Braille decoding rate of the blind is only 5%, and as the demand of the blind who want various forms of platforms or materials increases over time, development and product production for the blind are taking place. An example of product production is braille books, which seem to have more disadvantages than advantages, and unlike non-disabled people, it is true that access to information is still very difficult. In this paper, we designed a CNN-based Braille conversion and voice output device to make it easier for visually impaired people to obtain information than conventional methods. The device aims to improve the quality of life by allowing books, text images, or handwritten images that are not made in Braille to be converted into Braille through camera recognition, and designing a function that can be converted into voice according to the needs of the blind.

키워드

참고문헌

  1. S. A. Hwang and S. M. Lee, "A Study on the Utilization of Alternative Materials for the Visually Impaired Using Reading Aids Devices," Journal of the Korean BIBLIA Society for library and Information Science, Vol.13, No.3, pp.191-211, 2020.
  2. H. J. Kim, J. H. Moon, M. U. Song, S. M. Lee and K. S. Kong, "OnDot: Braille Training System for the Blind," The Institute of Internet, Broadcasting and Communication, Vol.20, No.6, pp.41-50, 2020.
  3. Y. I. Kim and H. W. Moon, "An Examination of the Current Status and Needs of Braille Literacy Education for Individuals with Adventitiously Visual Impairments," The Korean Journal of Visual Impairment, Vol.33, No.1, pp.1-29, 2017. https://doi.org/10.35154/kjvi.2017.33.1.1
  4. M. J. Yoon, J. H. Kang and K. H. Yu, "A Study of Walking Guide for the Blind by Tactile Display," Journal of Institute of Control, Robotics and Systems, Vol.13, No.8, pp.783-789, 2007. https://doi.org/10.5302/J.ICROS.2007.13.8.783
  5. H. J. Kim, Y. C. Kim, C. J. Park, S. J. Oh and B. J. Lee, "Auto Braille Translator using Matlab," The Journal of the Korea institute of electronic communication sciences, Vol.12, No.4, pp.691-700, 2017. https://doi.org/10.13067/JKIECS.2017.12.4.691
  6. J. Y. Lee and W. S. Cho, "A Study of Way guide System Design for a Visual Handicapped in School," Journal of the Korea Society of Computer and Information, Vol.15, No.4, pp.75-82, 2010. https://doi.org/10.9708/jksci.2010.15.4.075
  7. S. H. Seo and S. W. Jang, "Design and Implementation of a smart shoes module based on Arduino," Journal of the Korea Institute of Information and Communication Engineering, Vol.19, No.11, pp.2697-2702, 2015. https://doi.org/10.6109/JKIICE.2015.19.11.2697
  8. H. S. Lee and J. C. Oh, "Design and Implementation of a Small Server Room Environment Monitoring System by Using the Arduino," The Journal of the Korea institute of electronic communication sciences, Vol.12, No.2, pp.385-390, 2017. https://doi.org/10.13067/JKIECS.2017.12.2.385
  9. H. Y. Eom and K. H. Lee, "Design of Embodiment-based Programming Education using Arduino for Middle School Students," The Journal of the Convergence on Culture Technology, Vol.6, No.1, pp.471-476, 2020. https://doi.org/10.17703/JCCT.2020.6.1.471
  10. Y. G. Kim and E. Y. Cha, "Streamlined GoogLeNet Algorithm Based on CNN for Korean Character Recognition," Journal of the Korea Institute of Information and Communication Engineering, Vol.20, No.9, pp.1657-1665, 2016. https://doi.org/10.6109/jkiice.2016.20.9.1657
  11. J. H. Park, J. A. Kim, H. J. Kim and D. H. Kim, "CNN based modeling and classification for variety of apples," Journal of D-Culture Archives, Vol.4, No.1, pp.63-70, 2021. https://doi.org/10.23089/JDCA.2021.4.1.004
  12. T. Q. Hieu, S. H. Yeon and J. M. Kim, "Korean License Plate Recognition Using CNN," Journal of IKEEE, Vol.23, No.4, pp.1337-1342, 2019. https://doi.org/10.7471/IKEEE.2019.23.4.1337
  13. S. H. Choi, J. H. Kim, J. D. Oh and K. S. Kong, "A Smart Closet Using Deep Learning and Image Recognition for the Blind," The Journal of the Institute of Internet, Broadcasting and Communication, Vol.20, No.6, pp.51-58, 2020. https://doi.org/10.7236/JIIBC.2020.20.6.51
  14. H. G. Kim and Y. G. Choi, "Study on the Development of Working Safety Device for Visually Impaired Person," The Journal of Korea Institute of Information, Electronics, and Communication Technology, Vol.9, No.4, pp.366-372, 2016. https://doi.org/10.17661/JKIIECT.2016.9.4.366
  15. G. Y. Heo, "Implementation of an Arduino Compatible Modular Kit for Educational Purpose," Journal of the Korea Institute of Information and Communication Engineering, Vol.23, No.5, pp.547-554, 2019. https://doi.org/10.6109/JKIICE.2019.23.5.547
  16. C. G. Kim and J. M. Seo, "An Design and Implementation of Navigation System for Visually Impaired Persons Based on Smart Mobile Devices," The Journal of the Korea Contents Association, Vol.15, No.1, pp.24-30, 2015. https://doi.org/10.5392/JKCA.2015.15.01.024
  17. S. H. Choi and S. H. Jung, "Performance Improvement of Fake Discrimination using Time Information in CNN-based Signature Recognition," Journal of Digital Contents Society, Vol.19, No.1, pp.205-212, 2018. https://doi.org/10.9728/DCS.2018.19.1.205
  18. N. K. Lee, J. Y. Kim and J. H. Shim, "Empirical Study on Analyzing Training Data for CNN-based Product Classification Deep Learning Model," The Journal of Society for e-Business Studies, Vol.26, No.1, pp.107-126, 2021. https://doi.org/10.7838/JSEBS.2021.26.1.107