Journal of Convergence for Information Technology (융합정보논문지)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of Pre-Post Process for Accuraty Improvement of OCR Recognition Engine Based on Deep-Learning Technology

딥러닝 기반 OCR 인식 엔진의 정확도 향상을 위한 전/후처리기 기술 구현

  • Received : 2021.08.30
  • Accepted : 2022.01.20
  • Published : 2022.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

With the advent of the 4th Industrial Revolution, solutions that apply AI technology are being actively developed. Since 2017, the introduction of business automation solutions using AI-based Robotic Process Automation (RPA) has begun in the financial sector and insurance companies, and recently, it is entering a time when it spreads past the stage of introducing RPA solutions. Among the business automation using these RPA solutions, it is very important how accurately textual information in the document is recognized for business automation using various documents. Such character recognition has recently increased its accuracy by introducing deep learning technology, but there is still no recognition model with perfect recognition accuracy. Therefore, in this paper, we checked how much accuracy is improved when pre- and post-processor technologies are applied to deep learning-based character recognition engines, and implemented RPA recognition engines and linkage technologies.

4차산업 혁명이 도래함에 따라 AI 기술을 적용하는 솔루션 개발이 활발하게 이루어지고 있다. 2017년도부터 금융권, 보험사를 중심으로 AI 기반 RPA(Robotic Process Automation)을 이용한 업무 자동화 솔루션 도입이 이루어지기 시작했으며, 최근에는 RPA 솔루션 도입 단계를 지나 확산하는 시기로 진입하고 있다. 이러한 RPA 솔루션을 이용한 업무 자동화 중에서 각 종 문서들을 이용한 업무 자동화에는 문서내의 문자 정보를 얼마나 정확하게 인식하는지가 매우 중요하다. 이러한 문자 인식은 최근 딥러닝 기술을 도입함으로써 그 정확도가 많이 높아졌지만, 여전히 완벽한 인식 정확도 갖는 인식 모델은 존재하지 않는다. 따라서, 본 논문에서는 딥러닝 기반 문자 인식 엔진에 전/후 처리기 기술을 적용할 경우 얼마나 정확도가 향상되는지를 확인하고 RPA 인식 엔진과 연계 기술을 구현하였다.

Keywords

Acknowledgement

This research was supported through the Korea Industrial Technology Association(KOITA) funded by the Ministry of Science and ICT(MSIT)

References

  1. K. B. Kim. (2019). A Study of Convergence Technology in Robotic Process Automation for Task Automation. Journal of Convergence for Information Technology, 9(7), 8-13 DOI : /10.22156/CS4SMB.2019.9.7.008
  2. C. S. Lee. (2018). RPA, Changes to the Office, Current Status and Implications of RPA at Home and Abroad, DIGIECO. KT Economic Management Institute (Online). http://www.smallake.kr/wp-content/uploads/2018/08/rpa-office%EC%97%90-%EA%B0%80%EC%A0%B8%EB%8B%A4-%EC%A4%84-%EB%B3%80%ED%99%94201807191531982430925.pdf
  3. C. Kroll, A. Bujak, V. Darius, W. Enders & M. Esser. (2016). Robotic Process Automation-Robots conquer business processes in back offices. Capgemini Consulting, 1-48.
  4. Y. G. Hyun & J. Y. Lee. (2018). Trends Analysis and Future Direction of Business Process Automation, RPA (Robotic Process Automation) in the Times of Convergence. Journal of Digital Convergence, 16(11), 313-327. DOI : 10.14400/JDC.2018.16.11.313
  5. S. K. Lee & S. H. Hong. (2018). Can Analog weath er data be digitized with OCR?. Kakao AI Report (Online). https://brunch.co.kr/@kakao-it/319
  6. J. W. Kim, S. T. Kim, J. Y. Yoon & Y. I. Joo. (2015). A Personal Prescription Management System Employing Optical Character Recognition Technique. Journal of the Korea Institute of Information and Communication Engineering, 19(10), 2423-2428. DOI : 10.6109/jkiice.2015.19.10.2423
  7. J. H. Roh & D. S. Choi, (2014), Character recognition using a target string, Proceedings of Symposium of the Korean Institute of communications and Information Sciences,
  8. S. G. Hong, S. S Hwang & S. D. Kim. (2012). A license plate recognition system robust to vehicle location and viewing angle. Journal of the Institute of Electronics and Information Engineers, 49(12), 113-123. DOI : 10.5573/ieek.2012.49.12.113
  9. J. H. Ju & J. S. Oh, (2012). An adaptive binarization algorithm for degraded document images. Journal of Korean Institute of Communications and Information Sciences, 37(7), 581-585. DOI : 10.7840/KICS.2012.37.7A.581
  10. C. H. Son & H. M. Park. (2012). Fast multiple-image-based deblurring method. Journal of the Institute of Electronics Engineers of Korea SP, 49(4), 49-57.
  11. J. W. Song, N. R. Jung & H. S. Kang. (2015), Container BIC-code region extraction and recognition method using multiple thresholding. Journal of the Korea Institute of Information and Communication Engineering, 19(6), 1462-1470. DOI : 10.6109/jkiice.2015.19.6.1462
  12. G. C. Lee & J. S. Yoo. (2017), Development an Android based OCR Application for Hangul Food Menu. Journal of the Korea Institute of Information and Communication Engineering, 21 (5), 951-959. DOI : 10.6109/jkiice.2017.21.5.951