Movatterモバイル変換


[0]ホーム

URL:


Skip to main content

Advertisement

Springer Nature Link
Log in

Handwritten Digit String Recognition by Combination of Residual Network and RNN-CTC

  • Conference paper
  • First Online:

Part of the book series:Lecture Notes in Computer Science ((LNTCS,volume 10639))

Included in the following conference series:

Abstract

Recurrent neural network (RNN) and connectionist temporal classification (CTC) have showed successes in many sequence labeling tasks with the strong ability of dealing with the problems where the alignment between the inputs and the target labels is unknown. Residual network is a new structure of convolutional neural network and works well in various computer vision tasks. In this paper, we take advantage of the architectures mentioned above to create a new network for handwritten digit string recognition. First we design a residual network to extract features from input images, then we employ a RNN to model the contextual information within feature sequences and predict recognition results. At the top of this network, a standard CTC is applied to calculate the loss and yield the final results. These three parts compose an end-to-end trainable network. The proposed new architecture achieves the highest performances on ORAND-CAR-A and ORAND-CAR-B with recognition rates 89.75% and 91.14%, respectively. In addition, the experiments on a generated captcha dataset which has much longer string length show the potential of the proposed network to handle long strings.

This is a preview of subscription content,log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Similar content being viewed by others

References

  1. Diem, M., Fiel, S., Kleber, F., Sablatnig, R., Saavedra, J.M., Contreras, D., Barrios, J.M., Oliveira, L.S.: ICFHR 2014 competition on handwritten digit string recognition in challenging datasets (HDSRC 2014). In: 14th International Conference on Frontiers in Handwriting Recognition, pp. 779–784. IEEE Press, Crete (2014)

    Google Scholar 

  2. Gattal, A., Chibani, Y., Hadjadji, B.: Segmentation and recognition system for unknown-length handwritten digit strings. Pattern Anal. Appl.20, 307–323 (2017)

    Article MathSciNet  Google Scholar 

  3. Saabni, R.: Recognizing handwritten single digits and digit strings using deep architecture of neural networks. In: 3th International Conference on Artificial Intelligence and Pattern Recognition, pp. 1–6 (2016)

    Google Scholar 

  4. Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: 23th International Conference on Machine Learning, pp. 369–376 (2006)

    Google Scholar 

  5. Messina, R., Louradour, J.: Segmentation-free handwritten Chinese text recognition with LSTM-RNN. In 13th IAPR International Conference on Document Analysis and Recognition, pp. 171–175 (2015)

    Google Scholar 

  6. Wang, Q.-F., Yin, F., Liu, C.-L.: Handwritten chinese text recognition by integrating multiple contexts. IEEE Trans. Pattern Anal. Mach. Intell.34, 1469–1481 (2012)

    Article  Google Scholar 

  7. Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition (2016). doi:10.1109/TPAMI.2016.2646371

  8. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  9. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprintarXiv:1408.5093 (2014)

  10. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  11. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: 28th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)

    Google Scholar 

  12. Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprintarXiv:1312.4400 (2014)

  13. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput.9, 1735–1780 (1997)

    Article  Google Scholar 

  14. Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Netw.18, 602–610 (2005)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Shanghai Key Laboratory of Multidimensional Information Processing, Department of Computer Science and Technology, East China Normal University, Shanghai, 200062, China

    Hongjian Zhan, Qingqing Wang & Yue Lu

Authors
  1. Hongjian Zhan

    You can also search for this author inPubMed Google Scholar

  2. Qingqing Wang

    You can also search for this author inPubMed Google Scholar

  3. Yue Lu

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toYue Lu.

Editor information

Editors and Affiliations

  1. Guangdong University of Technology, Guangzhou, China

    Derong Liu

  2. Guangdong University of Technology, Guangzhou, China

    Shengli Xie

  3. South China University of Technology, Guangzhou, China

    Yuanqing Li

  4. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Dongbin Zhao

  5. King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia

    El-Sayed M. El-Alfy

Rights and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Zhan, H., Wang, Q., Lu, Y. (2017). Handwritten Digit String Recognition by Combination of Residual Network and RNN-CTC. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10639. Springer, Cham. https://doi.org/10.1007/978-3-319-70136-3_62

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only


[8]ページ先頭

©2009-2025 Movatter.jp