Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Research on Korea Text Recognition in Images Using Deep Learning

딥 러닝 기법을 활용한 이미지 내 한글 텍스트 인식에 관한 연구

  • 성상하 (동아대학교 경영정보학과) ;
  • 이강배 (동아대학교 경영정보학과) ;
  • 박성호 (동아대학교 경영정보학과)
  • Received : 2020.05.07
  • Accepted : 2020.06.20
  • Published : 2020.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, research on character recognition, which is one of the fields of computer vision, was conducted. Optical character recognition, which is one of the most widely used character recognition techniques, suffers from decreasing recognition rate if the recognition target deviates from a certain standard and format. Hence, this study aimed to address this limitation by applying deep learning techniques to character recognition. In addition, as most character recognition studies have been limited to English or number recognition, the recognition range has been expanded through additional data training on Korean text. As a result, this study derived a deep learning-based character recognition algorithm for Korean text recognition. The algorithm obtained a score of 0.841 on the 1-NED evaluation method, which is a similar result to that of English recognition. Further, based on the analysis of the results, major issues with Korean text recognition and possible future study tasks are introduced.

본 연구에서는 컴퓨터 비전의 분야 중 하나인 문자 인식에 관한 연구를 수행했다. 대표적인 문자인식 기법 중 하나인 광학식 문자 판독 기법의 경우 일정한 규격과 서식에서 벗어나게 되면 인식률이 떨어진다는 한계점이 있다. 따라서 본 연구에서는 딥 러닝 기법을 적용해 이러한 문제점을 해결하고자 한다. 또한 기존의 문자 인식 연구의 경우 대부분 영어 및 숫자 인식에 국한되어 있다. 따라서 본 연구는 한글 인식을 위한 딥 러닝 기반 문자 인식 알고리즘을 제시한다. 알고리즘은 1-NED 평가 방법에서 0.841의 점수를 얻었으며, 이는 영어 인식 결과와 비슷한 수치이다. 본 연구를 통해 딥 러닝 기반 한글 인식 알고리즘의 성능을 확인할 수 있으며, 이를 통해 향후 연구방향에 대해 제시한다.

Keywords

References

  1. H. J. Son & S. H. Kim. (2007). Machine Learning in Character Pattern Recognition. Communications of the Korean Institute of Information Scientists and Engineers, 25(3), 12-20. pISSN : 1229-6821
  2. K. S. Son, J. W. Kim & J. H. Lim. (2019). Convergence CCTV camera embedded with Deep Learning SW technology. Journal of the Korea Convergence Society, 10(1), 103-113. DOI : 10.15207/JKCS.2019.10.1.103
  3. Q. Ye & D. Doermann. (2014). Text Detection and Recognition in Imagery: A Survey. IEEE Transactions On Patern Analysis And Machine Inteligence, 37(7), 1480-1500. DOI : 10.1109/TPAMI.2014.2366765
  4. K. K. Kim, Y. Hur, G. M. Kim, W. H. Yu & H. S. Lim. (2017). Detail Focused Image Classifier Model for Traditional Images. Journal of the Korea Convergence Society, 8(12), 85-92. DOI : 10.15207/JKCS.2017.8.12.085
  5. J. S. Hwang, H. H. Jeon, S. H. Kim, & K. K. Kwon. (2017). OCR image recognition rate digital solution for prescription scanning. Proceedings of Korean Institute of Information Technology Conference. (pp. 379-381).
  6. S. H. Lee, J. H. Jeon, H. S. Hong, D. H. Kang & M. H. Park. (2017). Korean Prescription Character Recognition System Using OCR Technology. Proceedings of The Korean Institute of Information Scientists and Engineers Conference. (pp. 362-364).
  7. C. Y. Suen, S. Mori, H. C. Rim & P. S. P. Wang. (1998). Intriguing Aspects of Oriental Languages. International Journal of Pattern Recognition and Artificial Intelligence, 12(1), 5-29. DOI : 10.1142/S0218001498000038
  8. M. K. Kim & K. H. Lee. (1999). Design of Receipt Automation System Using OCR. Proceedings of The Korean Institute of Information Scientists and Engineers Conference. (pp. 531-533).
  9. S. W. Lee. (2002). Study on the selecting optimal artificial neural networks model prior to forecasting stock. master thesis, Inje University, Gyeongsangnam-do.
  10. K. D. Kim & Y. H. Kim. (2017). A Survey on Oil Spill and Weather Forecast Using Machine Learning Based on Neural Networks and Statistical Methods. Journal of the Korea Convergence Society, 8(10), 1-8. DOI : 10.15207/JKCS.2017.8.10.001
  11. Q. Li, W. Cai, X. Wang, Y. Zhou, D. D. Feng & M. Chen. (2014). Medical image classification with convolutional neural network. International Conference on Control Automation Robotics & Vision. (pp. 844-848). DOI : 10.1109/ICARCV.2014.7064414
  12. O. Janssens et al. (2016). Convolutional Neural Network Based Fault Detection for Rotating Machinery. Journal of Sound and Vibration, 377, 331-345. DOI : 10.1016/J.JSV.2016.05.027
  13. Y. Lecun, L. Bottou, Y. Bengio & P. Haffner. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324. DOI : 10.1109/5.726791
  14. P. Liu, X. Qiu & X. Huang. (2016). Recurrent Neural Network for Text Classification with Multi-Task Learning. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence.
  15. B. Shi, X. Bai & C. Yao. (2017). An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2297-2304. DOI : 10.1109/TPAMI.2016.2646371
  16. Y. G. Kim & E. Y. Cha. (2016). Streamlined GoogLeNet Algorithm Based on CNN for Korean Character Recognition. Journal of the Korea Institute of Information and Communication Engineering, 20(9), 1657-1685. DOI : 10.6109/jkiice.2016.20.9.1657
  17. B. Shi, M. Yang, X. Wang. P. Lyu, C. Yao & X. Bai (2019). ASTER: An Attentional Scene Text Recognizer with Flexible Rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(9), 2035-2048. DOI : 10.1109/TPAMI.2018.2848939