A Comparison between Multi-Layer Perceptrons and Convolutional Neural Networks for Text Image Super-Resolution

Clément Peyrard, Franck Mamalet, Christophe Garcia

2015

Abstract

We compare the performances of several Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (ConvNets) for single text image Super-Resolution. We propose an example-based framework for both MLP and ConvNet, where a non-linear mapping between pairs of patches and high-frequency pixel values is learned. We then demonstrate that for equivalent complexity, ConvNets are better than MLPs at predicting missing details in upsampled text images. To evaluate the performances, we make use of a recent database (ULR-textSISR-2013a) along with different quality measures. We show that the proposed methods outperforms sparse coding-based methods for this database.

References

  1. Ahmed, F., Gustafson, S., and Karim, M. (1995). Highfidelity image interpolation using radial basis function neural networks. In Proceedings of the IEEE 1995 National Aerospace and Electronics Conference, volume 2, pages 588-592.
  2. Carcenac, M. (2007). A modular neural network for super-resolution of human faces. Applied Intelligence, 30(2):168-186.
  3. Cheeseman, P., Kanefsky, B., Kraft, R., Stutz, J., and Hanson, R. (1996). Super-resolved surface reconstruction from multiple images. In Maximum Entropy and Bayesian Methods, pages 293-308. Springer.
  4. Dalley, G., Freeman, B., and Marks, J. (2004). Single-frame text super-resolution: a bayesian approach. In International Conference on Image Processing, volume 5, pages 3295-3298 Vol. 5.
  5. Donaldson, K. and Myers, G. (2005). Bayesian SuperResolution of Text in Video with a Text-Specific Bimodal Prior. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:1188- 1195.
  6. Dong, C., Loy, C. C., He, K., and Tang, X. (2014). Learning a deep convolutional network for image superresolution. In Computer Vision-ECCV 2014, pages 184-199. Springer.
  7. Fan, W., Sun, J., Naoi, S., Minagawa, A., and Hotta, Y. (2012). Local Consistency Constrained Adaptive Neighbor Embedding for Text Image SuperResolution. 10th IAPR International Workshop on Document Analysis Systems, pages 90-94.
  8. Freeman, W., Jones, T., and Pasztor, E. (2002). Examplebased super-resolution. Computer Graphics and Applications, IEEE, 22(2):56-65.
  9. Gao, J., Guo, Y., and Yin, M. (2013). Restricted boltzmann machine approach to couple dictionary training for image super-resolution. In IEEE International Conference on Image Processing, pages 499-503.
  10. Garcia, C. and Delakis, M. (2004). Convolutional face finder: A neural architecture for fast and robust face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(11):1408-1423.
  11. Glasner, D., Bagon, S., and Irani, M. (2009). Superresolution from a single image. IEEE 12th International Conference on Computer Vision, pages 349- 356.
  12. Irani, M. and Peleg, S. (1991). Improving resolution by image registration. CVGIP: Graph. Models Image Process., 53(3):231-239.
  13. LeCun, Y. and Bengio, Y. (1995). Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361.
  14. Luong, H. Q. and Philips, W. (2007). Non-local text image reconstruction. In Ninth International Conference on Document Analysis and Recognition, volume 1, pages 546-550.
  15. Mancas-Thillou, C., Mirmehdi, M., and Copernic, A. (2005). Super-resolution text using the teager filter. First International Workshop on Camera-Based Document Analysis and Recognition, pages 10-16.
  16. Nakashika, T., Takiguchi, T., and Ariki, Y. (2013). HighFrequency Restoration Using Deep Belief Nets for Super-resolution. International Conference on SignalImage Technology & Internet-Based Systems, pages 38-42.
  17. Nasrollahi, K. and Moeslund, T. (2014). Super-resolution: a comprehensive survey. Machine Vision and Applications, 25(6):1423-1468.
  18. Nayef, N., Chazalon, J., Gomez-Krämer, P., and Ogier, J. (2014). Efficient example-based super-resolution of single text images based on s elective patch processing. In 11th International Workshop on Document Analysis Systems, pages 227-231.
  19. Pan, F. and Zhang, L. (2003). New image super-resolution scheme based on residual error restoration by neural networks. Optical Engineering, 42(10):3038-3046.
  20. Panagiotopoulou, A. and Anastassopoulos, V. (2007). Scanned images resolution improvement using neural networks. Neural Computing and Applications, 17(1):39-47.
  21. Peleg, T. and Elad, M. (2014). A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution. IEEE Transactions on Image Processing, 7149(c):1-1.
  22. Plaziac, N. (1999). Image interpolation using neural networks. Trans. Img. Proc., 8(11):1647-1651.
  23. Protter, M., Elad, M., Takeda, H., and Milanfar, P. (2009). Generalizing the nonlocal-means to super-resolution reconstruction. Image Processing, IEEE Transactions on, 18(1):36-51.
  24. Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6):386.
  25. Stark, H. and Oskoui, P. (1989). High-resolution image recovery from image-plane arrays, using convex projections. J. Opt. Soc. Am. A, 6(11):1715-1726.
  26. Sun, J., Xu, Z., and Shum, H.-Y. (2011). Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Transactions on Image Processing, 20(6):1529-1542.
  27. Thouin, P. D. and Chang, C.-I. (2000). A method for restoration of low-resolution document images. International Journal on Document Analysis and Recognition, 2(4):200-210.
  28. Timofte, R., De, V., and Gool, L. V. (2013). Anchored Neighborhood Regression for Fast Example-Based Super-Resolution. IEEE International Conference on Computer Vision, pages 1920-1927.
  29. Walha, R., Drira, F., Lebourgeois, F., and Alimi, A. M. (2012). Super-resolution of single text image by sparse representation. In Proceeding of the workshop on Document Analysis and Recognition, pages 22-29. ACM.
  30. Yang, J., Wang, Z., Lin, Z., Cohen, S., and Huang, T. (2012). Coupled dictionary training for image superresolution. IEEE Transactions on Image Processing, 21(8):3467-3478.
  31. Yang, J., Wright, J., Huang, T. S., and Ma, Y. (2010). Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11):2861- 2873.
  32. Zheng, Y., Kang, X., Li, S., He, Y., and Sun, J. (2014). Realtime document image super-resolution by fast matting. In 11th IAPR International Workshop on Document Analysis Systems, pages 232-236.
Download


Paper Citation


in Harvard Style

Peyrard C., Mamalet F. and Garcia C. (2015). A Comparison between Multi-Layer Perceptrons and Convolutional Neural Networks for Text Image Super-Resolution . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 84-91. DOI: 10.5220/0005297200840091


in Bibtex Style

@conference{visapp15,
author={Clément Peyrard and Franck Mamalet and Christophe Garcia},
title={A Comparison between Multi-Layer Perceptrons and Convolutional Neural Networks for Text Image Super-Resolution},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={84-91},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005297200840091},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - A Comparison between Multi-Layer Perceptrons and Convolutional Neural Networks for Text Image Super-Resolution
SN - 978-989-758-089-5
AU - Peyrard C.
AU - Mamalet F.
AU - Garcia C.
PY - 2015
SP - 84
EP - 91
DO - 10.5220/0005297200840091