Character recognition of mixed convex-concave braille points and legibility of deteriorated braille points

被引:0
|
作者
Oyama, Yoshifumi [1 ]
Tajima, Toshihisa [1 ]
Koga, Hiroaki [1 ]
机构
[1] Applied Electronics Research Cent, Kumamoto, Japan
关键词
Theoretical; (THR);
D O I
10.1002/(SICI)1520-684X(199702)28:23.0.CO;2-R
中图分类号
学科分类号
摘要
Braille is an important communication code for blind people. The automatic recognition of braille is adapted to convex braille points. This paper describes the technology for recognizing mixed convex and concave braille points that result from typing on both sides of a sheet of paper. The braille points are recognized by scanning only one side and are translated into the kana syllabary. Convex points can be distinguished from concave points by the highlights and shadow patterns generated by exposing the braille points to LED light. The braille points which form one character are extracted by applying an extraction mask. The recognition performance of this method is evaluated by using the prototype system in the presence of deformed braille points, deteriorated paper, and slanting paper. The recognition ratio is estimated to be more than 96 percent for five different braille patterns prepared by various typing methods, including a braille printer.
引用
收藏
页码:44 / 53
相关论文
共 26 条
  • [2] Monotone ε-subgradient method used to search saddle points of convex-concave functions
    Rzhevskij, S.V.
    1993, (04): : 89 - 100
  • [3] Deep Learning Strategy for Braille Character Recognition
    Kausar, Tasleem
    Manzoor, Sajjad
    Kausar, Adeeba
    Lu, Yun
    Wasif, Muhammad
    Ashraf, M. Adnan
    IEEE ACCESS, 2021, 9 : 169357 - 169371
  • [4] Braille Character Recognition Based on Neural Networks
    Smelyakov, Kirill
    Chupryna, Anastasiya
    Yeremenko, Dmytro
    Sakhon, Anton
    Polezhai, Vitalii
    2018 IEEE SECOND INTERNATIONAL CONFERENCE ON DATA STREAM MINING & PROCESSING (DSMP), 2018, : 509 - 513
  • [5] Braille Document Parameters Estimation for Optical Character Recognition
    Tai, Zhenfei
    Cheng, Samuel
    Verma, Pramode
    ADVANCES IN VISUAL COMPUTING, PT II, PROCEEDINGS, 2008, 5359 : 905 - 914
  • [6] Braille Character Recognition Using Find Contour Method
    Subur, Joko
    Sardjono, Tri Arief
    Mardiyanto, Ronny
    5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING AND INFORMATICS 2015, 2015, : 699 - 703
  • [7] THE MIXED CONVEX-CONCAVE EFFECT ON THE REGULARITY OF A BOLTZMANN SOLUTION
    An, Gayoung
    Lee, Donghyun
    SIAM JOURNAL ON MATHEMATICAL ANALYSIS, 2025, 57 (01) : 1086 - 1136
  • [8] Braille Character Recognition Using Generalized Feature Vector Approach
    Bhattacharya, J.
    Majumder, S.
    COMPUTER NETWORKS AND INTELLIGENT COMPUTING, 2011, 157 : 171 - 180
  • [9] BrailleReader: Braille Character Recognition Using Wearable Motion Sensor
    Liu, Xiaochen
    Li, Fan
    Cao, Yetong
    Wang, Yu
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (11) : 10538 - 10553
  • [10] Fixed points of generalized φ-concave-convex operators with mixed monotonicity and applications
    Xu, Shaoyuan
    Fan, Li
    Han, Yan
    AIMS MATHEMATICS, 2024, 9 (11): : 32442 - 32462