Advertisement

Deep Learning for Optical Character Recognition and Its Application to VAT Invoice Recognition

  • Yu Wang
  • Guan GuiEmail author
  • Nan Zhao
  • Yue Yin
  • Hao Huang
  • Yunyi Li
  • Jie Wang
  • Jie Yang
  • Haijun Zhang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 517)

Abstract

Optical character recognition (OCR) is considered as one of long-term and hot research topics due to the fact that OCR technique can change the documents from paper to computer-readable format by consistently growing. However, the recognition accuracy of current OCR technique is required to improve some special applications such as in reimbursement of value-added tax (VAT) invoices. This paper proposes two OCR techniques by using deep convolutional neural network (CNN) and residual network (ResNet), respectively. According to our test dataset, the formerly proposed techniques can reach up to 97.08%, while the latter can increase to 99.38%.

Keywords

Optical character recognition Value-added tax invoices Deep learning Convolutional neural network Residuals network 

References

  1. 1.
    Modi, H., Scholar, P.G., Parikh, M.C.: A review on optical character recognition techniques. Int. J. Comput. Appl. 160(6), 975–8887 (2017)Google Scholar
  2. 2.
    Sawant, A.S., Chougule, D.G.: Script independent text pre-processing and segmentation for OCR. In: International Conference on Electrical, Electronics, Signals, Communication and Optimization (EESCO), pp. 1–5 (2015)Google Scholar
  3. 3.
    Mohammad, F., Anarase, J., Shingote, M., Ghanwat, P.: Optical character recognition implementation using pattern matching. Int. J. Comput. Sci. Inform. Technol. 5(2), 2088–2090 (2014)Google Scholar
  4. 4.
    Yi, C., Tian, Y.: Scene text recognition in mobile applications by character descriptor and structure configuration. IEEE Trans. Image Process. 23(7), 2972–2982 (2014)MathSciNetCrossRefGoogle Scholar
  5. 5.
    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. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298–2304 (2017)CrossRefGoogle Scholar
  6. 6.
    Wigington, C., Stewart, S., Davis, B., Barrett, B., Price, B., Cohen, S.: Data augmentation for recognition of handwritten words and lines using a CNN-LSTM network. In: In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 639–645 (2017)Google Scholar
  7. 7.
    Vairalkar, M.K.: Edge detection of images using Sobel operator. Int. J. Emerg. Technol. Adv. Eng. 2(1), 291–293 2012Google Scholar
  8. 8.
    Tabatabai, A.J., Mitchell, O.R.: Edge location to subpixel values in digital imagery. IEEE Trans. Pattern Anal. Mach. Intell. 6(2), 188–201 (1984)CrossRefGoogle Scholar
  9. 9.
    Gupta, M.R., Jacobson, N.P., Garcia, E.K.: OCR binarization and image pre-processing for searching historical documents. Pattern Recogn. 40(2), 389–397 (2007)CrossRefGoogle Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1–9 (2012)Google Scholar
  11. 11.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  12. 12.
    Ohta, M., Takasu, A., Adachi, J.: Retrieval methods for English-text with miss recognized OCR characters. In: International Conference on Document Analysis and Recognition, pp. 950–956 (1997)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Yu Wang
    • 1
  • Guan Gui
    • 1
    Email author
  • Nan Zhao
    • 1
  • Yue Yin
    • 1
  • Hao Huang
    • 1
  • Yunyi Li
    • 1
  • Jie Wang
    • 1
  • Jie Yang
    • 1
  • Haijun Zhang
    • 1
  1. 1.College of Telecommunication and Information EngineeringNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations