Enhancing the Ensemble-Based Scene Character Recognition by Using Classification Likelihood

  • Fuma HorieEmail author
  • Hideaki Goto
  • Takuo Suganuma
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12047)


Research on scene character recognition has been popular for its potential in many applications including automatic translator, signboard recognition, and reading assistant for the visually-impaired. The scene character recognition is challenging and difficult owing to various environmental factors at image capturing and complex design of characters. Current OCR systems have not gained practical accuracy for arbitrary scene characters, although some effective methods were proposed in the past. In order to enhance existing recognition systems, we propose a hierarchical recognition method utilizing the classification likelihood and image pre-processing methods. It is shown that the accuracy of our latest ensemble system has been improved from 80.7% to 82.3% by adopting the proposed methods.


Hierarchical recognition method Ensemble voting classifier Synthetic Scene Character Data 


  1. 1.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  2. 2.
    Bay, S.D.: Combining nearest neighbor classifiers through multiple feature subsets. In: Proceedings of ICML 1998, pp. 37–45 (1998)Google Scholar
  3. 3.
    Kim, H., Pang, S., Je, H., Kim, D., Bang, S.Y.: Constructing support vector machine ensemble. Pattern Recognit. 36(12), 2757–2767 (2003)CrossRefGoogle Scholar
  4. 4.
    Hansen, L.K., Salamon, P.: Neural network ensemble. IEEE Trans. Pattern Anal. Mach. Intell. 12(10), 993–1001 (1990)CrossRefGoogle Scholar
  5. 5.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)zbMATHGoogle Scholar
  6. 6.
    Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: Workshop on Deep Learning, NIPS (2014)Google Scholar
  7. 7.
    Ren, X., Chen, K., Sun, J.: A CNN based scene chinese text recognition algorithm with synthetic data engine. arXiv preprint arXiv:1604.01891 (2016)
  8. 8.
    Horie, F., Goto, H.: Synthetic scene character generator and multi-scale voting classifier for Japanese scene character recognition. In: Proceedings of IVCNZ 2018 (2018)Google Scholar
  9. 9.
    Yi, C., Yang, X., Tian, Y.: Feature representations for scene text character recognition. In: Proceedings of ICDAR 2013, pp. 907–911 (2013)Google Scholar
  10. 10.
    Horie, F., Goto, H.: Japanese scene character recognition using random image feature and ensemble scheme. In: Proceedings of ICPRAM 2019, vol. 1, pp. 414–420 (2019)Google Scholar
  11. 11.
    Tumor, K., Ghosh, J.: Theoretical foundations of linear and order statistics combiners for neural pattern classifiers. Technical report TR-95-02-98, Computer and Vision Research Center, University of Texas, Austin (1995)Google Scholar
  12. 12.
    Li, P., Peng, L., Wen, J.: Rejecting character recognition errors using CNN based confidence estimation. Chin. J. Electron. 25(3), 520–526 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Graduate School of Information SciencesTohoku UniversitySendaiJapan
  2. 2.Cyberscience CenterTohoku UniversitySendaiJapan

Personalised recommendations