The Journal of Supercomputing

, Volume 75, Issue 4, pp 1941–1952 | Cite as

Improving personal information detection using OCR feature recognition rate

  • YoungKyung Lee
  • Jinho Song
  • Yoojae WonEmail author


With the recent advancements in information and communication technologies, the creation and storage of documents has become digitalized. Therefore, many documents are stored on computers. Documents containing personal information can be leaked by internal or external malicious acts, and the problem of information loss for individuals and corporations is gradually increasing. This paper proposes a method to more efficiently and quickly identify the existence of personal information among documents stored in image files on personal and corporate computers to prevent their leakage in advance. We improved the efficiency of personal information detection by classifying optical character recognition (OCR) features by recognition rate and deleting redundant ones to increase detection speed. In addition, the detection time was reduced using the reference frequency of the classified OCR features. Experiments confirm an improvement in the performance of the proposed method compared with that of the existing system.


Character recognition Personal information Image files Regular expression Text learning Data classification Data reuse 



This study was supported by a research fund of Chungnam National University.


  1. 1.
    Ham DS, Lee DR, Choi KU, Oh IS (2010) Printed Hangul recognition with adaptive hierarchical structures depending on 6-types. Int J Contents 10(1):10–18Google Scholar
  2. 2.
    Katiyar G (2016) A hybrid recognition system for off-line handwritten characters. Hum Centric Comput Inf Sci 5(1):357Google Scholar
  3. 3.
    Mishra TK, Majhi B, Dash R (2017) A contour descriptors-based generalized scheme for handwritten Odia numerals recognition. J Inf Process Syst 13(1):174–183Google Scholar
  4. 4.
    Giltae L (2003) A study on machine printed character recognition based on character type classification. J Inst Electron Eng Korea 5(4):26–39Google Scholar
  5. 5.
    Gerber C, Chung M (2016) Number plate detection with a multi-convolutional neural network approach with optical character recognition for mobile devices. J Inf Process Syst 12(1):100–108Google Scholar
  6. 6.
    Choi JH, Shin HS, Nasridinov A (2017) A comparative study on data mining classification techniques for military applications. J Converg 7(2):1–10Google Scholar
  7. 7.
    Youngkyung L (2016) A study on detecting personal information in the image files. Proc Korean Soc Internet Inf 17(2):213–214Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Science EngineeringChungnam National UniversityDaejeonSouth Korea

Personalised recommendations