The Journal of the Korea Contents Association (한국콘텐츠학회논문지)

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Improved Handwritten Hangeul Recognition using Deep Learning based on GoogLenet

GoogLenet 기반의 딥 러닝을 이용한 향상된 한글 필기체 인식

  • 김현우 (한국외국어대학교 컴퓨터, 전자시스템공학부) ;
  • 정유진 (한국외국어대학교 컴퓨터, 전자시스템공학부)
  • Received : 2018.05.28
  • Accepted : 2018.07.02
  • Published : 2018.07.28
Download PDF
⟨ Previous Next ⟩

Abstract

The advent of deep learning technology has made rapid progress in handwritten letter recognition in many languages. Handwritten Chinese recognition has improved to 97.2% accuracy while handwritten Japanese recognition approached 99.53% percent accuracy. Hanguel handwritten letters have many similar characters due to the characteristics of Hangeul, so it was difficult to recognize the letters because the number of data was small. In the handwritten Hanguel recognition using Hybrid Learning, it used a low layer model based on lenet and showed 96.34% accuracy in handwritten Hanguel database PE92. In this paper, 98.64% accuracy was obtained by organizing deep CNN (Convolution Neural Network) in handwritten Hangeul recognition. We designed a new network for handwritten Hangeul data based on GoogLenet without using the data augmentation or the multitasking techniques used in Hybrid learning.

딥 러닝 기술의 등장으로 여러 나라의 필기체 인식은 높은 정확도 (중국어 필기체 인식은 97.2%, 일본어 필기체 인식은 99.53%)를 보인다. 하지만 한글 필기체는 한글의 특성으로 유사글자가 많은데 비해 문자의 데이터 수는 적어 글자 인식에 어려움이 있다. 하이브리드 러닝을 통한 한글 필기체 인식에서는 lenet을 기반으로 하여 낮은 레이어를 가진 모델을 사용하여 한글 필기체 데이터베이스 PE92에서 96.34%의 정확도를 보여주었다. 본 논문에서는 하이브리드 러닝에서 사용하였던 데이터 확장 기법(data augmentation)이나 multitasking을 사용하지 않고도 GoogLenet 네트워크를 기본으로 한글 필기체 데이터에 적합한 더 깊고 더 넓은 CNN(Convolution Neural Network) 네트워크를 도입하여 PE92 데이터베이스에서 98.64%의 정확도를 얻었다.

Keywords

References

  1. In-Jung Kim and Xiaohui Xie, "Handwritten Hangul recognition using deep convolutional neural networks," International Journal on Document Analysis and Recognition (IJDAR), Vol.18, No.1, pp.1-13, 2015. https://doi.org/10.1007/s10032-014-0229-4
  2. In-Jung Kim, Changbeom Choi, and Sang-Heon Lee, "Improving discrimination ability of convolutional neural networks by hybrid learning," International Journal on Document Analysis and Recognition (IJDAR), Vol.19, No.1, pp.1-9, 2016. https://doi.org/10.1007/s10032-015-0256-9
  3. Weixin Yang, Lianwen Jin, Zecheng Xie, and Ziyong Feng, "Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge," Document Analysis and Recognition (ICDAR), pp.551-555, 2015.
  4. Charlie Tsai, Recognizing Handwritten Japanese Characters Using Deep Convolutional Neural Networks, Technical Report, Stanford University, pp.1-7, 2016.
  5. Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner, "Gradient- based learning applied to document recognition," Proceedings of the IEEE, Vol.86, No.11, pp.2278-2324, 1998. https://doi.org/10.1109/5.726791
  6. 강우영, 김병희, 장병탁, "인셉션 모듈 기반의 보다 깊은 컨볼루션 신경망을 통한 한글 필기체 인식," 한국정보과학회 학술발표논문집, pp.883-885, 2016.
  7. Christian Szegedy, Wei Liu, Yangquing Jia, and Pierre Sermanet, Scott Reed, "Going deeper with convolutions," Proceedings of the IEEE conference on computer vision and pattern recognition, pp1-9, 2015(6).
  8. Christian Szegedy, Vincent Vanhoucke. Sergey Ioffe, and Jon Shlens, "Rethinking the inception architecture for computer vision," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2818-2826, 2016.
  9. Kaiming He, Xiangyu, Zhang, Shaoquing Ren, and Jian Sun, "Deep residual learning for image recognition," Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778, 2016.
  10. Vinod Nair and Geoffrey E. Hinton, "Rectified linear units improve restricted boltzmann machines," Proceedings of the 27th international conference on machine learning (ICML-10), pp.807-814, 2010.
  11. Zhou Wang and Alan C. Bovik, "Mean squared error: Love it or leave it? A new look at signal fidelity measures," IEEE signal processing magazine, Vol.26, No.1, pp.98-117, 2009. https://doi.org/10.1109/MSP.2008.930649
  12. Pieter-Tjerk De Boer, Dirk P. Kroese, Shie Mannor, and Reuven Y. Rubinstein, "A tutorial on the cross-entropy method," Annals of operations research, Vol.134, No.1, pp.19-67, 2005. https://doi.org/10.1007/s10479-005-5724-z
  13. Diederik P. Kingma and Jimmy Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
  14. Sergey Ioffe and Christian Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," arXiv preprint arXiv:1502.03167, 2015.
  15. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Rusian Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," Journal of machine learning research, Vol.15, No.1, pp.1929-1958, 2014.
  16. Ankit Sharma and Dipti R. Chaudhary, "Character recognition using neural network," International Journal of Engineering Trends and Technology (IJETT), Vol.4, pp.662-667, 2013.