The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time Printed Text Detection System using Deep Learning Model

딥러닝 모델을 활용한 실시간 인쇄물 문자 탐지 시스템

  • Ye-Jun Choi ;
  • Song-Won Kim ;
  • Mi-Kyeong Moon (Dept. Software, Dongseo University)
  • 최예준 (동서대학교 ) ;
  • 김송원 (동서대학교 ) ;
  • 문미경 (동서대학교 소프트웨어학과)
  • Received : 2024.04.17
  • Accepted : 2024.06.12
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Online, such as web pages and digital documents, have the ability to search for specific words or specific phrases that users want to search in real time. Printed materials such as printed books and reference books often have difficulty finding specific words or specific phrases in real time. This paper describes the development of a deep learning model for detecting text and a real-time character detection system using OCR for recognizing text. This study proposes a method of detecting text using the EAST model, a method of recognizing the detected text using EasyOCR, and a method of expressing the recognized text as a bounding box by comparing a specific word or specific phrase that the user wants to search for. Through this system, users expect to find specific words or phrases they want to search in real time in print, such as books and reference books, and find necessary information easily and quickly.

웹페이지나 디지털 문서 등과 같은 온라인에서는 사용자가 검색하고 싶은 특정 단어나 특정 문구를 실시간으로 검색하는 기능이 있다. 인쇄된 도서나 참고서 등과 같은 인쇄물에는 실시간으로 특정 단어나 특정 문구를 찾는 기능이 없어 어려움을 겪는 경우가 많다. 본 논문에서는 텍스트를 탐지(Detection)하는 딥러닝 모델과 텍스트를 인식(Recognition)하는 OCR을 활용한 실시간 문자 탐지 시스템의 개발내용에 관해 기술한다. 본 연구에서는 EAST 모델을 사용하여 텍스트를 탐지하는 방법, 탐지한 텍스트를 EasyOCR을 사용하여 인식하는 방법, 인식한 텍스트를 사용자가 검색하고 싶은 특정 단어나 특정 문구를 비교하여 bounding box로 나타내는 방법을 제안한다. 이 시스템을 통해 사용자는 도서나 참고서 등과 같은 인쇄물에서 실시간으로 검색하고 싶은 특정 단어나 특정 문구를 찾아 필요한 정보를 쉽고 빠르게 찾는 것에 효과적일 것을 기대한다.

Keywords

Acknowledgement

본 논문은 2024년 과학기술정보통신부 및 정보통신기획평가원의 SW중심대학사업의 연구결과로 수행되었음" (2019-0-01817)

References

  1. S. Lee, "'Aging Korea'...People in their 70s and older, more than in their 20s," Article, 2024. 
  2. J. Kim and J. Kim, "A Study of Health Care System Housing and Environment of the Elderly," J. Korea Institute of Electronic Communication Sciences, vol. 7, no. 4, 2012, pp. 925-930. 
  3. S. Park, "Will digital technology solve the inconvenience of 'small letters'," Article, 2021. 
  4. W. Kim, "A Study on the Prediction for the OCR Technology Development Trajectory based on the Patent and Article Information," Ph.D. thesis, the general graduate school of the Korea National University of Technology and Education, 2023. 
  5. C. Yoon, "The study of Authorized / Unauthorized Vehicle Recognition System using Image Recognition with Neural Network," J. of the Korea Institute of Electronic Communication Sciences, vol. 15, no. 2, 2020, pp. 299-306. 
  6. J. Han, G. Kim, W. Son, M. Lee, and Y. Park, "The study of Parking Management System by Image Processing," J. of the Korea Institute of Electronic Communication Sciences, vol. 12, no. 4, 2017, pp. 651-656. 
  7. J. Park, S. Choi, J. Kim, S. Jung, and C. Sim, "Implementation of a Drug Information Retrieval System Through OCR API pErformance Comparison," J. of the Korea Institute of Electronic Communication Sciences, vol. 18, no. 5, 2023, pp. 989-998. 
  8. M. Choi and M. Moon, "Analysis System for Public Interest Report Video of Traffic Law Violation based on Deep Learning Algorithms," J. of the Korea Institute of Electronic Communication Sciences, vol. 18, no. 1, 2023, pp. 63-70. 
  9. Z. Xinyu, Y. Cong, W. He, W. Yuzhi, Z. Shuchang, H. Weiran, and L. Jiajun, "EAST: An Efficient and Accurate Scene Text Detector," IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, USA, 2017, pp. 2642-2651. 
  10. C. Kim, S. An, E. Jeon, and B. Cha, "A Study on the Survey and Demonstration Test of OCR based on Open Source for AI OCR," Proc. Symp. Korean Institute of communications and Information Sciences, Gangwon, Korea, 2022, pp. 1124-1126. 
  11. C. Kim, K. Kim, K. Oh, and Y. Yoon, "Design of Digit Recognition System on a Formalized Answer Sheet Using Deep Learning," Academic Presentation Papers of the Korean Society of Information Science, Jeju, Korea, 2023, pp. 851-852. 
  12. S. Kim, J. Park, S. Kim, Y. Na, and Y. Jang, "Multi-book Label Detection Model using Object Detection and OCR," J. Korean Institute of Information Technology, vol. 21, no. 2, 2023, pp. 1-8. 
  13. C. Park, Y. Lim, S. Jeong, Y. Cho, B. Lee, G. Lee, and J. Kim, "YOLO, EAST : Comparison of Scene Text Detection Performance, Using a Neural Network Model," The Transactions of the Korea Information Processing Society (KTSDE), vol. 11, no. 3, 2022, pp. 115-124.