Braille Document Parameters Estimation for Optical Character Recognition

被引:0
作者
Tai, Zhenfei [1 ]
Cheng, Samuel [1 ]
Verma, Pramode [1 ]
机构
[1] Univ Oklahoma, Sch Elect & Comp Engn, Norman, OK 73019 USA
来源
ADVANCES IN VISUAL COMPUTING, PT II, PROCEEDINGS | 2008年 / 5359卷
关键词
Braille image; Radon transform; optical character recognition; skewness; line-spacing;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
There is a significant need for a system to recognize Braille documents in order to preserve them and make them available to a larger group of visually impaired people. We introduce a high-adaptive Braille documents parameters estimation method to automatically determine the skewness, indentations, and spacing in both vertical and horizontal directions. The key element in determining the skewness of the images, is based on Radon transform, which is generated from the integral of a function over straight lines, and is nicely applied in this case since Braille documents are highly directional. We demonstrate the effectiveness of skewness correction as well as the accuracy of indentation and spacing in both orientations. The proposed algorithm is an essential component of character recognition of Braille document discussed in this paper.
引用
收藏
页码:905 / 914
页数:10
相关论文
共 50 条
[31]   A Novel Approach to Printed Arabic Optical Character Recognition [J].
Mansoor A. Al Ghamdi .
Arabian Journal for Science and Engineering, 2022, 47 :2219-2237
[32]   The DSFPN, a new neural network for optical character recognition [J].
Morns, IP ;
Dlay, SS .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (06) :1465-1473
[33]   Undergraduate research support with optical character recognition apps [J].
Hahn, Jim .
REFERENCE SERVICES REVIEW, 2014, 42 (02) :336-+
[34]   Optical Character Recognition Guided Image Super Resolution [J].
Hildebrandt, Philipp ;
Schulze, Maximilian ;
Cohen, Sarel ;
Doskoc, Vanja ;
Saabni, Raid ;
Friedrich, Tobias .
PROCEEDINGS OF THE 2022 ACM SYMPOSIUM ON DOCUMENT ENGINEERING, DOCENG 2022, 2022,
[35]   Open source optical character recognition for historical research [J].
Blanke, Tobias ;
Bryant, Michael ;
Hedges, Mark .
JOURNAL OF DOCUMENTATION, 2012, 68 (05) :659-683
[36]   Distributed Optical Character Recognition for Old Romanian Prints [J].
Pop, Daniel ;
Irimie, Bogdan ;
Petcu, Dana .
2017 19TH INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC 2017), 2017, :416-418
[37]   α-Shape Based Classification with Applications to Optical Character Recognition [J].
Packer, Eli ;
Tzadok, Asaf ;
Kluzner, Vladimir .
11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, :344-348
[38]   Optical Character Recognition using Convolutional Neural Network [J].
Shreya, Sakshi ;
Upadhyay, Yash ;
Manchanda, Mohit ;
Vohra, Rubeena ;
Singh, Gagan Deep .
PROCEEDINGS OF THE 2019 6TH INTERNATIONAL CONFERENCE ON COMPUTING FOR SUSTAINABLE GLOBAL DEVELOPMENT (INDIACOM), 2019, :55-59
[39]   Backpropagation based optical character recognition of medieval documents [J].
Ivelin, S ;
Ieroham, B ;
Gortcheva, E .
ARTIFICIAL INTELLIGENCE: METHODOLOGY, SYSTEMS, APPLICATIONS, 1996, 35 :141-147
[40]   Deep Learning for Optical Character Recognition and Its Application to VAT Invoice Recognition [J].
Wang, Yu ;
Gui, Guan ;
Zhao, Nan ;
Yin, Yue ;
Huang, Hao ;
Li, Yunyi ;
Wang, Jie ;
Yang, Jie ;
Zhang, Haijun .
COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, CSPS 2018, VOL III: SYSTEMS, 2020, 517 :87-95