Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Streamlined GoogLeNet Algorithm Based on CNN for Korean Character Recognition

한글 인식을 위한 CNN 기반의 간소화된 GoogLeNet 알고리즘 연구

  • Kim, Yeon-gyu (Department of Computer Science Engineering, Pusan National University) ;
  • Cha, Eui-young (Department of Computer Science Engineering, Pusan National University)
  • Received : 2016.04.25
  • Accepted : 2016.05.09
  • Published : 2016.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Various fields are being researched through Deep Learning using CNN(Convolutional Neural Network) and these researches show excellent performance in the image recognition. In this paper, we provide streamlined GoogLeNet of CNN architecture that is capable of learning a large-scale Korean character database. The experimental data used in this paper is PHD08 that is the large-scale of Korean character database. PHD08 has 2,187 samples for each character and there are 2,350 Korean characters that make total 5,139,450 sample data. As a training result, streamlined GoogLeNet showed over 99% of test accuracy at PHD08. Also, we made additional Korean character data that have fonts that are not in the PHD08 in order to ensure objectivity and we compared the performance of classification between streamlined GoogLeNet and other OCR programs. While other OCR programs showed a classification success rate of 66.95% to 83.16%, streamlined GoogLeNet showed 89.14% of the classification success rate that is higher than other OCR program's rate.

CNN(Convolutional Neural Network)을 사용한 심화 학습이 다양한 분야에서 진행되고 있으며 관련 연구들은 이미지 인식의 많은 분야에서 높은 성능을 보이고 있다. 본 논문에서는 한글 인식을 위해 대규모 한글 데이터베이스를 학습할 수 있는 CNN 구조의 간소화된 GoogLeNet을 사용한다. 본 논문에 사용된 데이터베이스는 대규모 한글 데이터베이스인 PHD08로 총 2,350개의 한글 문자에 대해 각 2,187개의 샘플을 가져 총 5,139,450개의 데이터로 구성되어 있다. 간소화된 GoogLeNet은 학습의 결과로 학습 종료 시점에서 PHD08에 대해 99% 이상의 Top-1 테스트 정확도를 보였으며 실험의 객관성을 높이기 위해 PHD08에 존재하지 않는 한글 폰트로 이루어진 한글 데이터를 제작하여 상용 OCR 프로그램들과 분류 성능을 비교하였다. 상용 OCR 프로그램들은 66.95%에서 83.17%의 분류 성공률을 보인 반면, 제안하는 간소화된 GoogLeNet은 평균 89.14%의 분류 성공률을 보여 상용 OCR 프로그램들보다 높은 분류 성공률을 보였다.

Keywords

References

  1. D. Ciresan, U. Meier, J. Masci and J. Schmidhuber, "Multicolumn deep neural network for traffic sign classification," Neural Networks, vol. 32, pp. 333-338, Aug. 2012. https://doi.org/10.1016/j.neunet.2012.02.023
  2. N. Kalchbrenner, E. Grefenstette and P. Blunsom, "A Convolutional Neural Network for Modelling Sentences," arXiv preprint arXiv:1404.2188, 2014.
  3. P. Callet, C. Viard-Gaudin and D. Barba, "A Convolutional Neural Network Approach for Objective Video Quality Assessment," IEEE Transactions on Neural Networks, vol. 17, no. 5, pp. 1316-1327, Sep. 2006. https://doi.org/10.1109/TNN.2006.879766
  4. Y. Zhang, "Deep Convolutional Network for Handwritten Chinese Character Recognition," University of Stanford, CS231N course project.
  5. Z. Zhong, L. Jin and Z. Xie, "High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature map," in Document Analysis and Recognition(ICDAR), 13th International Conference on IEEE, pp. 846-850, May 2015.
  6. W. Yang, L. Jin, Z. Xie and Z. Feng, "Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge," in Document Analysis and Recognition (ICDAR), 13th International Conference on. IEEE, pp. 551-555, May 2015.
  7. D. Ham, D. Lee, I. Jung and I. Oh, "Construction of Printed Hangul Character Database PHD08," Journal of the korea contents association, vol. 8, no. 11, pp.33-40, Nov. 2008. https://doi.org/10.5392/JKCA.2008.8.11.033
  8. B. Sin and J. Kim, "On-line Handwritten Character Recognition with Hidden Markov Models," in proceeding of the Korea Information Science Society, pp. 533-542, Oct. 1992.
  9. J. Ha and B. Shin, "Optimization of Number of States in HMM for On-line Hangul Recognition," in Proceeding of the Korea Information Science Society, vol. 25, no. 2, pp. 372-374, Oct. 1998.
  10. T. Hwang and S. Kim, "Hangul Recognition Using The Path Following Algorithm," IE interfaces, vol. 3, no. 2, pp. 53-62, Oct. 1990.
  11. I. Kim and X. Xiaohui, "Handwritten Hangul recognition using deep convolutional neural network," International Journal on Document Analysis and Recognition (IJDAR), vol. 18, no. 1, pp. 1-13, Mar. 2015. https://doi.org/10.1007/s10032-014-0229-4
  12. Y. LeCun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," in Proceeding of the IEEE 86.11, pp. 2278-2324, 1998.
  13. ImageNet Large Scale Visual Recognition Challenge [Internet]. Available: http://image-net.org/.
  14. A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Network," in Proceeding of the Neural Information Processing Systems 25(NIPS), pp. 1097-1105, 2012.
  15. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, "Going deeper with convolutions," in Proceeding of the Computer Vision and Pattern Recognition (CVPR), pp. 1-9, 2015.
  16. S. Arora, A. Bhaskara, R. Ge and T. Ma, "Provable Bounds for Learning Some Deep Representations," CoRR (Computing Research Repository), abs/1310.6343, 2013.
  17. Recognition Technologies and Innovation Ace (RETIA) ABBYYFineReader12 [Internet]. Available: http://www.retia.co.kr/cnt/products/products.html?category=1&uid=24&name=finereader-12&tab=1.
  18. ABC-OCR [Internet]. Available: https://itunes.apple.com/us/app/scanner-ocr-optical-character/id777913435?mt=8.
  19. Office Lens [Internet]. Available: https://itunes.apple.com/en/app/office-lens/id975925059?mt=8.
  20. Linear Interpolation [Internet]. Available: https://en.wikipedia.org/wiki/Linear_interpolation.
  21. CAFFE(Convolutional Architecture for Fast Feature Embedding) [Internet]. Available: http://caffe.berkeleyvision.org/.

Cited by

  1. 딥 러닝 기반 쇼핑몰 플랫폼용 상품 이미지 자동 분류 시스템 및 사용성 평가 vol.17, pp.3, 2017, https://doi.org/10.7236/jiibc.2017.17.3.227
  2. O2O 쇼핑몰 플랫폼 서비스디자인을 위한 딥 러닝 기반의 이미지 검색 시스템 vol.15, pp.7, 2017, https://doi.org/10.14400/jdc.2017.15.7.213
  3. 병 인식 및 보증금 환불을 위한 분류 알고리즘 vol.21, pp.9, 2016, https://doi.org/10.6109/jkiice.2017.21.9.1744
  4. 딥 러닝 기법을 활용한 이미지 내 한글 텍스트 인식에 관한 연구 vol.11, pp.6, 2020, https://doi.org/10.15207/jkcs.2020.11.6.001