A Method for Document Image Binarization based on Histogram Matching and Repeated Contrast Enhancement

Mattias Wahde

2014

Abstract

In this paper, a new method for binarization of document images is introduced. During training, the method stores histograms from training images (divided into small tiles), along with the optimal binarization threshold. Training image tiles are presented in pairs, one noisy version and one clean binarized version, where the latter is used for finding the optimal binarization threshold. During use, the method considers the tiles of an image one by one. It matches the stored histograms to the histogram for the tile that is to be binarized. If a sufficiently close match is found, the tile is binarized using the corresponding threshold associated with the stored histogram. If no match is found, the contrast of the tile is slightly enhanced, and a new attempt is made. This sequence is repeated until either a match is found, or a (rare) timeout is reached. The method has been applied to a set of test images, and has been shown to outperform several comparable methods.

References

  1. Chen, K.-N., Chen, C.-H., and Chang, C.-C. (2012). Efficient illumination compensation techniques for text images. Digital Signal Processing, 22:726-733.
  2. González, A. and Bergasa, L. (2013). A text reading algorithm for natural images. Image and vision computing, 31:255-274.
  3. Kennedy, J. and Eberhart, R. C. (1995). Particle swarm optimization. In Proceedings of the IEEE International Conference on Neural Networks, pages 1942-1948.
  4. Lu, S., Su, B., and Tan, C. (2010). Document image binarization using background estimation and stroke edges. International Journal on Document Analysis and Recogntion, 13(4):303-314.
  5. Neumann, L. and Matas, J. (2010). A method for text localization and recognition in real-world images. In 10th Asian Conference on Computer Vision (ACCV2010), LNCS 6495, pages 2067-2078.
  6. Niblack, W. (1986). An Introduction to Image Processing. Prentice-Hall.
  7. Otsu, N. (1979). A threshold selection method from graylevel histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9:62-66.
  8. Pele, O. and Werman, M. (2010). The quadratic-chi histogram distance family. In 11th European Conference on Computer Vision (ECCV2010), LNCS 6312, pages 749-762.
  9. Sauvola, J. and Pietikäinen, M. (2000). Adaptive document image binarization. Pattern Recognition, 33:225-236.
  10. Shi, J., Ray, N., and Zhang, H. (2012). Shape based local thresholding for binarization of document images. Pattern Recognition Letters, 33:24-32.
  11. Stathis, P., Kavallieratou, E., and Papamarkos, N. (2008). An evaluation technique for binarization algorithms. Journal of Universal Computer Science, 14(18):3011-3030.
  12. Valizadeh, M. and Kabir, E. (2013). An adaptive water flow model for binarization of degraded document images. International Journal on Document Analysis and Recogntion, 16(2):165-176.
Download


Paper Citation


in Harvard Style

Wahde M. (2014). A Method for Document Image Binarization based on Histogram Matching and Repeated Contrast Enhancement . In Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-015-4, pages 34-41. DOI: 10.5220/0004753100340041


in Bibtex Style

@conference{icaart14,
author={Mattias Wahde},
title={A Method for Document Image Binarization based on Histogram Matching and Repeated Contrast Enhancement},
booktitle={Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2014},
pages={34-41},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004753100340041},
isbn={978-989-758-015-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - A Method for Document Image Binarization based on Histogram Matching and Repeated Contrast Enhancement
SN - 978-989-758-015-4
AU - Wahde M.
PY - 2014
SP - 34
EP - 41
DO - 10.5220/0004753100340041