Advertisement

PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters

  • Qun LiuEmail author
  • Edward Collier
  • Supratik Mukhopadhyay
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11853)

Abstract

Due to the sparsity of features, noise has proven to be a great inhibitor in the classification of handwritten characters. To combat this, most techniques perform denoising of the data before classification. In this paper, we consolidate the approach by training an all-in-one model that is able to classify even noisy characters. For classification, we progressively train a classifier generative adversarial network on the characters from low to high resolution. We show that by learning the features at each resolution independently a trained model is able to accurately classify characters even in the presence of noise. We experimentally demonstrate the effectiveness of our approach by classifying noisy versions of MNIST [13], handwritten Bangla Numeral, and Basic Character datasets [5, 6].

Keywords

Progressively training General adversarial networks Classification Noisy characters Handwritten bangla 

References

  1. 1.
    Aref, W.G., Samet, H.: Decomposing a window into maximal quadtree blocks. Acta Inf. 30(5), 425–439 (1993)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Basu, S., Ganguly, S., Mukhopadhyay, S., DiBiano, R., Karki, M., Nemani, R.R.: Deepsat: A learning framework for satellite imagery. In: Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems, Bellevue, WA, USA, 3–6 November 2015Google Scholar
  3. 3.
    Basu, S., et al.: Learning sparse feature representations using probabilistic quadtrees and deep belief nets. Neural Process. Lett. 45(3), 855–867 (2017)CrossRefGoogle Scholar
  4. 4.
    Basu, S., et al.: A theoretical analysis of deep neural networks for texture classification. In: 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, BC, Canada, 24–29 July 2016, pp. 992–999 (2016)Google Scholar
  5. 5.
    Bhattacharya, U., Chaudhuri, B.B.: Handwritten numeral databases of indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Anal. Mach. Intell. 31(3), 444–457 (2009)CrossRefGoogle Scholar
  6. 6.
    Bhattacharya, U., Shridhar, M., Parui, S.K., Sen, P., Chaudhuri, B.: Offline recognition of handwritten bangla characters: an efficient two-stage approach. Pattern Anal. Appl. 15(4), 445–458 (2012)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Boureau, Y.L., Cun, Y.L., et al.: Sparse feature learning for deep belief networks. In: Advances in Neural Information Processing Systems, pp. 1185–1192 (2008)Google Scholar
  8. 8.
    Collier, E., DiBiano, R., Mukhopadhyay, S.: CactusNets: Layer applicability as a metric for transfer learning. In: 2018 International Joint Conference on Neural Networks, IJCNN 2018, Rio de Janeiro, Brazil, 8–13 July 2018, pp. 1–8 (2018)Google Scholar
  9. 9.
    Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 2672–2680. Curran Associates, Inc. (2014). http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf
  10. 10.
    Hariharan, B., Arbeláez, P., Girshick, R., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 447–456 (2015)Google Scholar
  11. 11.
    Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018–3027 (2017)Google Scholar
  12. 12.
    Huang, K., Aviyente, S.: Sparse representation for signal classification. NIPS 19, 609–616 (2006)Google Scholar
  13. 13.
    Karki, M., Liu, Q., DiBiano, R., Basu, S., Mukhopadhyay, S.: Pixel-level reconstruction and classification for noisy handwritten bangla characters. In: 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, Niagara Falls, NY, USA, 5–8 August 2018, pp. 511–516 (2018).  https://doi.org/10.1109/ICFHR-2018.2018.00095
  14. 14.
    Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. CoRR abs/1710.10196 (2017). http://arxiv.org/abs/1710.10196
  15. 15.
    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
  16. 16.
    LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)CrossRefGoogle Scholar
  17. 17.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  18. 18.
    Markas, T., Reif, J.: Quad tree structures for image compression applications. Inf. Process. Manage. 28(6), 707–721 (1992)CrossRefGoogle Scholar
  19. 19.
    Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015)Google Scholar
  20. 20.
    Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2642–2651. JMLR. org (2017)Google Scholar
  21. 21.
    Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536–2544 (2016)Google Scholar
  22. 22.
    Su, J., Vargas, D.V., Sakurai, K.: One pixel attack for fooling deep neural networks. In: Arxiv (2018)Google Scholar
  23. 23.
    Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp. 3320–3328 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Qun Liu
    • 1
    Email author
  • Edward Collier
    • 1
  • Supratik Mukhopadhyay
    • 1
  1. 1.Louisiana State UniversityBaton RougeUSA

Personalised recommendations