skip to main content
research-article

Hyper Parameter Optimization of CRNN for Printed Devanagari Script Recognition using Taguchi's Method

Published:25 March 2023Publication History
Skip Abstract Section

Abstract

The Devanagari script is one of the most widely used scripts worldwide. The existing deep learning-based optical character recognition system for printed Devanagari scripts using Convolutional Neural Network – Recurrent Neural Network, or CRNN is not robust enough to recognize any randomly printed Devanagari scanned document. At present, the hyper-parameters of the CRNN system are selected randomly either with the trial-and-error or grid search methods. Moreover, there is no optimized way to choose the hyper-parameters of the CRNN, which improves the recognition accuracy for Devanagari documents. Furthermore, the lack of standard Devanagari script datasets has hampered the development of word recognizers. In this paper, the hyper-parameter of the CRNN system is optimized using Taguchi's method of optimization. The performance of the hyper-parameters optimized CRNN system is compared with the current state-of-the-art text recognition CRNN network. The results reveal that the CRNN optimized with Taguchi's method performs better than the CRNN-based systems.

REFERENCES

  1. [1] Vaughan Don. The World's 5 Most Commonly Used Writing Systems. https://www.britannica.com/list/the-worlds-5-most-commonly-used-writing-systems.Google ScholarGoogle Scholar
  2. [2] Bansal V. and Sinha R. M. K.. 1999. Partitioning and searching dictionary for correction of optically read Devanagari character strings. In Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR. 653656.Google ScholarGoogle ScholarCross RefCross Ref
  3. [3] Bansal V. and Sinha R. M. K.. 2000. Integrating knowledge sources in Devanagari text recognition system. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans 30, 4 (2000), 500505.Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. [4] Karayil T., Ul-Hasan A., and Breuel T. M.. 2015. A segmentation-free approach for printed Devanagari script recognition. In 13th International Conference on Document Analysis and Recognition (ICDAR). IEEE, 946950.Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. [5] Chavan V., Malage A., Mehrotra K., and Gupta M. K.. 2017. Printed text recognition using BLSTM and MDLSTM for Indian languages. In Fourth International Conference on Image Information Processing (ICIIP). 16.Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Sankaran N. and Jawahar C. V.. 2012. Recognition of printed Devanagari text using BLSTM neural network. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR’12). 322325.Google ScholarGoogle Scholar
  7. [7] Badrinarayanan V., Kendall A., and Cipolla R.. 2017. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 12 (2017), 24812495.Google ScholarGoogle Scholar
  8. [8] Graves A., Fernández S., Gomez F., and Schmidhuber J.. 2006. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd International Conference on Machine Learning. 369376.Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. [9] Liu H., Jin S., and Zhang C.. 2018. Connectionist temporal classification with maximum entropy regularization. Advances in Neural Information Processing Systems (2018), 31.Google ScholarGoogle Scholar
  10. [10] Mathew M., Mohit J., and Jawahar C. V.. 2017. Benchmarking scene text recognition in Devanagari, Telugu, and Malayalam. In 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE, 4246.Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Yang H. F., Dillon T. S., and Chen Y. P. P.. 2016. Optimized structure of the traffic flow forecasting model with a deep learning approach. IEEE Trans. Neural Netw. Learn. Syst. 28, 10 (2016), 23712381.Google ScholarGoogle ScholarCross RefCross Ref
  12. [12] Palit S., Chaudhuri B. B., Das P. P., and Chatterjee B. N.. 1995. A feature-based scheme for the machine recognition of printed Devanagari script. In Pattern Recognition, Image Processing, and Computer Vision (1995), 163168.Google ScholarGoogle Scholar
  13. [13] Pal U. and Chaudhuri B.. 1997. Printed devanagari script OCR system. Vivek-Bombay-. 10 (1997), 1224.Google ScholarGoogle Scholar
  14. [14] Pal U.. 2004. Indian script character recognition: A survey. Pattern Recognition 37 (2004), 18871899.Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Shaw B., Kumar Parui S., and Shridhar M.. 2008. Online handwritten Devanagari word recognition: A holistic approach based on directional chain code feature and HMM. In International Conference on Information Technology, (ICIT'08). IEEE, 23208.Google ScholarGoogle Scholar
  16. [16] Bansal V. and Sinha R. M. K.. 2001. A complete OCR for printed Hindi text in Devanagari script. Proceedings of Sixth International Conference on Document Analysis and Recognition. IEEE Computer Society.Google ScholarGoogle ScholarCross RefCross Ref
  17. [17] Garain U. and Chaudhuri B. B.. 2002. Segmentation of touching characters in printed Devanagari and Bangla scripts using fuzzy multi factorial analysis. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 32, 4 (2001), 449459.Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] He K., Zhang X., Ren S., and Sun J.. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770778.Google ScholarGoogle ScholarCross RefCross Ref
  19. [19] Szegedy C., Ioffe S., Vanhoucke V., and Alemi A. A.. 2017. Inception-v4, inception-ResNet and the impact of residual connections on learning. In Proceedings of the AAAI Conference on Artificial Intelligence.Google ScholarGoogle ScholarCross RefCross Ref
  20. [20] Krizhevsky A., Sutskever I., and Hinton G. E.. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NIPS). 10971105.Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Akhter S. S. M. N. and Rege P. P.. 2021. Multi-task learning for pre-processing of printed Devanagari document images with hyper-parameter optimization of the deep architecture using Taguchi method. Sadhana 46, 3 (2021), 124.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Carbune V., Gonnet P., Deselaers T., Rowley H. A., Daryin A., Calvo M., Wang L. L., Keysers D., Feuz S., and Gervais P.. 2020. Fast multi-language LSTM-based online handwriting recognition. International Journal on Document Analysis and Recognition (IJDAR) 23, 2 (2020), 89102.Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. [23] Mehrotra K., Gupta M. K., and Khajuria K.. 2019. Collaborative deep neural network for printed text recognition of Indian languages. In Fifth International Conference on Image Information Processing (ICIIP). 252256.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Zhang X., Chen X., Yao L., Ge C., and Dong M.. 2019. Deep neural network hyper-parameter optimization with orthogonal array tuning. In Proceedings of the International Conference on Neural Information Processing. Cham: Springer, 287295.Google ScholarGoogle ScholarCross RefCross Ref
  25. [25] Young S. R., Rose D. C., Karnowski T. P., Lim S. H., and Patton R. M.. 2015. Optimizing deep learning hyper-parameters through an evolutionary algorithm. In Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments. 15.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Ilievski I., Akhtar T., Feng J., and Shoemaker C. A.. 2017. Efficient hyperparameter optimization for deep learning algorithms using deterministic RBF surrogates. In Proceedings of the Thirty-first AAAI Conference on Artificial Intelligence.Google ScholarGoogle ScholarDigital LibraryDigital Library
  27. [27] Li L., Jamieson K., DeSalvo G., Rostamizadeh A., and Talwalkar A.. 2017. Hyperband: A novel bandit-based Sådhanå (2021) approach to hyperparameter optimization. J. Mach. Learn. Res. 18, 1 (2017), 67656816.Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Bergstra J. and Bengio Y.. 2012. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13 (2012), 281305.Google ScholarGoogle ScholarDigital LibraryDigital Library
  29. [29] Taguchi G. and Phadke M. S.. 1989. Quality engineering through design optimization. In Quality Control, Robust Design, and the Taguchi Method. Boston, MA: Springer, 7796.Google ScholarGoogle Scholar
  30. [30] Taguchi G. and Yokoyama Y.. 1993. Taguchi Methods: Design of Experiments. Taguchi Methods Series 4.Google ScholarGoogle Scholar
  31. [31] Bagchi T. P.. 1993. Taguchi Methods Explained: Practical Steps to Robust Design. Hoboken: Prentice-Hall.Google ScholarGoogle Scholar
  32. [32] Shi B., Bai X., and Yao C.. 2016. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 11 (2016), 22982304.Google ScholarGoogle ScholarDigital LibraryDigital Library
  33. [33] Ioffe S. and Szegedy C.. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. PMLR, 448456.Google ScholarGoogle Scholar
  34. [34] Joseph R. et al. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarGoogle Scholar
  35. [35] Kingma D. P. and Ba J.. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.Google ScholarGoogle Scholar
  36. [36] Nwankpa C., Ijomah W., Gachagan A., and Marshall S.. 2018. Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378.Google ScholarGoogle Scholar
  37. [37] Srivastava N., Hinton G., Krizhevsky A., Sutskever I., and Salakhutdinov R.. 2014. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (2014), 19291958.Google ScholarGoogle ScholarDigital LibraryDigital Library
  38. [38] Werbos P. J.. 1990. Backpropagation through time: What it does and how to do it. Proceedings of the IEEE 78, 10 (1990), 15501560.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Zhang X., Chen X., Yao L., Ge C., and Dong M.. 2019. Deep neural network hyperparameter optimization with orthogonal array tuning. In Gedeon T., Wong K., Lee M., (Eds). 2019. Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol. 1142. Springer, Cham, Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Lin C. J., Jeng S. Y., and Lee C. L.. 2021. Hyperparameter optimization of deep learning networks for classification of breast histopathology images. Sensors and Materials 33, 1 (2021), 315325.Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Munger T. and Desa S.. 2020. A statistical design of experiments approach to machine learning model selection in engineering applications. ASME. J. Comput. Inf. Sci. Eng. February 21, 1 (2020), 011008. Google ScholarGoogle ScholarCross RefCross Ref
  42. [42] Gunna S., Saluja R., and Jawahar C. V.. 2021. Transfer learning for scene text recognition in Indian languages. In International Conference on Document Analysis and Recognition, Springer, Cham, 182197.Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Hyper Parameter Optimization of CRNN for Printed Devanagari Script Recognition using Taguchi's Method

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access

    • Published in

      cover image ACM Transactions on Asian and Low-Resource Language Information Processing
      ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 22, Issue 4
      April 2023
      682 pages
      ISSN:2375-4699
      EISSN:2375-4702
      DOI:10.1145/3588902
      Issue’s Table of Contents

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 25 March 2023
      • Online AM: 19 January 2023
      • Accepted: 19 December 2022
      • Received: 25 June 2022
      Published in tallip Volume 22, Issue 4

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article
    • Article Metrics

      • Downloads (Last 12 months)96
      • Downloads (Last 6 weeks)18

      Other Metrics

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    View Full Text

    HTML Format

    View this article in HTML Format .

    View HTML Format
    About Cookies On This Site

    We use cookies to ensure that we give you the best experience on our website.

    Learn more

    Got it!