Abstract
This work is concerned with the binarization of document images caputured by MultiSpectral Imaging (MSI) systems. The documents imaged are historical manuscripts and MSI is used to gather more information compared to traditional RGB photographs or scans. The binarization method proposed makes use of a state-of-the-art binarization algorithm, which is applied on a single image taken from the stack of multispectral images. This output is then combined with the output of a target detection algorithm. The target detection method is named Adaptive Coherence Estimator (ACE) and it is used to improve the binarization performance. Numerical results show that the combination of both algorithms leads to a performance increase. Additionally, the results exhibit that the method performs partially better than other binarization methods designed for grayscale and multispectral images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Cisz, A.P., Schott, J.R.: Performance comparison of hyperspectral target detection algorithms in altitude varying scenes. In: SPIE Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XI, vol. 5806 (2005)
Cohen, Y., August, Y., Blumberg, D.G., Rotman, S.R.: Evaluating subpixel target detection algorithms in hyperspectral imagery. J. Electrical and Computer Engineering 2012 (2012)
Gatos, B., Pratikakis, I., Perantonis, S.J.: Adaptive degraded document image binarization. Pattern Recognition 39(3), 317–327 (2006)
Harsanyi, J.C.: Detection and classification of subpixel spectral signatures in hyperspectral image sequences. Ph.D. thesis, Dept. Elect. Eng. University of Maryland, Baltimore County (1993)
Hedjam, R., Cheriet, M.: Historical document image restoration using multispectral imaging system. Pattern Recognition 46(8), 2297–2312 (2013)
Hedjam, R., Cheriet, M., Kalacska, M.: Constrained energy maximization and self-referencing method for invisible ink detection from multispectral historical document images. In: ICPR, pp. 3026–3031 (2014)
Hollaus, F., Gau, M., Sablatnig, R.: Enhancement of multispectral images of degraded documents by employing spatial information. In: ICDAR, pp. 145–149 (2013)
Howe, N.R.: A laplacian energy for document binarization. In: ICDAR, pp. 6–10 (2011)
Lettner, M., Sablatnig, R.: Higher order mrf for foreground-background separation in multi-spectral images of historical manuscripts. In: Document Analysis Systems, pp. 317–324 (2010)
Mitianoudis, N., Papamarkos, N.: Multi-spectral document image binarization using image fusion and background subtraction techniques. In: ICIP, pp. 5172–5176 (2014)
Moghaddam, R.F., Cheriet, M.: A multi-scale framework for adaptive binarization of degraded document images. Pattern Recognition 43(6), 2186–2198 (2010)
Moghaddam, R.F., Cheriet, M.: Adotsu: An adaptive and parameterless generalization of otsu’s method for document image binarization. Pattern Recognition 45(6), 2419–2431 (2012)
Moghaddam, R.F., Cheriet, M.: A multiple-expert binarization framework for multispectral images. CoRR abs/1502.01199 (2015)
Otsu, N.: A Threshold Selection Method from Gray-level Histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1), 62–66 (1979)
Rivest-Hénault, D., Moghaddam, R.F., Cheriet, M.: A local linear level set method for the binarization of degraded historical document images. IJDAR 15(2), 101–124 (2012)
Salerno, E., Tonazzini, A., Bedini, L.: Digital image analysis to enhance underwritten text in the archimedes palimpsest. IJDAR 9(2–4), 79–87 (2007)
Scharf, L., McWhorter, L.: Adaptive matched subspace detectors and adaptive coherence estimators. In: Conference Record of the Thirtieth Asilomar Conference on Signals, Systems and Computers, vol. 2, pp. 1114–1117 (1996)
Su, B., Lu, S., Tan, C.L.: Binarization of historical document images using the local maximum and minimum. In: DAS, pp. 159–166 (2010)
Theiler, J., Foy, B.R., Fraser, A.M.: Beyond the adaptive matched filter: nonlinear detectors for weak signals in high-dimensional clutter. In: SPIE Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIII, vol. 6565, pp. 656503–656503-12 (2007)
West, J.E., Messinger, D.W., Ientilucci, E.J., Kerekes, J.P., Schott, J.R.: Matched filter stochastic background characterization for hyperspectral target detection. In: SPIE Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XI, vol. 5806, pp. 1–12 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hollaus, F., Diem, M., Sablatnig, R. (2015). Binarization of MultiSpectral Document Images. In: Azzopardi, G., Petkov, N. (eds) Computer Analysis of Images and Patterns. CAIP 2015. Lecture Notes in Computer Science(), vol 9257. Springer, Cham. https://doi.org/10.1007/978-3-319-23117-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-23117-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23116-7
Online ISBN: 978-3-319-23117-4
eBook Packages: Computer ScienceComputer Science (R0)