Abstract
In this paper, we present an effective coarse-to-fine algorithm to recognize the degraded Chinese characters. The algorithm contains two basic steps. Firstly, for the test images and the train images, reduce the dimension of the character feature via principal component analysis (PCA), and K-nearest neighbor classifier is exploited to find the candidate recognition results. Secondly, a sparse representation algorithm is explored as a fine recognition classifier. A dictionary is constructed by the PCA feature spaces of all the training images of the candidates’ categories to reconstruct the input image via sparse representation, and the residual error is calculated by the sparse coefficients corresponding to each candidate category. We apply the method to the low resolution and noised 3755 categories of Chinese characters, the comparison experiments verify the efficacy of the proposed algorithm.
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.
References
Liu, C.M., Wang, C.H., et al.: Low resolution character recognition by image quality evaluation. In: 18th International Conference on Pattern Recognition. Proceedings, vol. 1, pp. 864–867 (2006)
Sun, J., Hotta, Y., et al.: Camera based degraded text recognition using grayscale feature. In: 8th International Conference on Document Analysis and Recognition. Proceedings, vol. 1 and vol. 2, pp. 182–186 (2005)
Yanadume, S., Mekada, Y., et al.: Recognition of very low-resolution characters from motion images captured by a portable digital camera. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds.) PCM 2004. LNCS, vol. 3331, pp. 247–254. Springer, Heidelberg (2004)
Sun, J., Huang, K., Hotta, Y., Fujimoto, K., Naoi, S.: Degraded Character Recognition by Complementary Classifiers Combination. In: 9th International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 579–583 (2007)
Sun, J., Hotta, Y., Sun, J.: Low resolution character recognition by dual eigenspace and synthetic degraded patterns. In: ACM (ed.) HDP 2004, pp. 15–22 (2004)
Omachi, S., Aso, H.: A qualitative adaptation of subspace method for character recognition. IEICE Trans. J82-D-II(11), 1930–1939 (1999)
Murase, H., Kimura, H., Yoshimura, M., Miyake, Y.: An improvement of the auto-correlation matrix in the pattern matching method and its application to handprinted “HIRAGANA” recognition. IECE Trans. J64-D(3), 276–283 (1981)
Uchida, S., Sakoe, H.: Handwritten character recognition using elastic matching based on a class-dependent deformation model. In: Proc. ICDAR, vol. 1 of 2, pp. 163–167 (2003)
Luong, H.Q., Philips, W.: Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour. International Journal on Document Analysis and Recognition 11, 39–51 (2008)
Thouin, P.D., Chang, C.-I.: A method for restoration of low-resolution document images. International Journal on Document Analysis and Recognition 2, 200–210 (2000)
Cannon, M., Hochberg, J., Kelly, P.: Quality assessment and restoration of typewritten document images. International Journal on Document Analysis and Recognition 2, 80–89 (1999)
Taylor, M.J., Dance, C.R.: Enhancement of document images from cameras. In: Proc. Of SPIE, vol. 23305, pp. 230–241 (1998)
Kanungo, T., Haralick, R.M., Baird, H.S., Choi, Y.W., Chi, S.Y., Kim, K.K., Chung, Y.K.: A statistical, nonparametric methodology for document degradation model validation. IEEE. Trans. PAMI 22, 1209–1223 (2002)
Wang, L., Pavlidis, T.: Direct gray-scale extraction of features for character recognition. IEEE Trans. PAMI 15, 1053–1066 (1993)
Lee, S.-W., Kim, Y.-J.: Direct Extraction of Topographic Features for Gray Scale Character Recognition. IEEE Trans. PAMI 17, 724–729 (1995)
Wright, J., et al.: Robust Face Recognition via Sparse Representation. IEEE Transactions on PAMI 31, 210–227 (2009)
Tropp, J.A., Gilbert, A.C.: Signal recovery from random measurements via orthogonal matching pursuit. IEEE Transactions on Information Theory 53, 4655–4666 (2007)
Needell, D., Vershynin, R.: Uniform Uncertainty Principle and Signal Recovery via Regularized Orthogonal Matching Pursuit. Foundations of Computational Mathematics 9, 317–334 (2009)
Needell, D., Vershynin, R.: Signal Recovery From Incomplete and Inaccurate Measurements Via Regularized Orthogonal Matching Pursuit. IEEE Journal of Selected Topics in Signal Processing 4, 310–316 (2010)
Donoho, D., Tsaig, Y., Drori, I., Starck, J.C.: Sparse solution of underdetermined linear equations by stagewise orthogonal matching pursuit. IEEE Trans. Inf. Theory (2006) (submitted)
Candes, E.J., et al.: Stable signal recovery from incomplete and inaccurate measurements. Communications on Pure and Applied Mathematics 59, 1207–1223 (2006)
Donoho, D.L.: For most large underdetermined systems of linear equations the minimal l(1)-norm solution is also the sparsest solution. Communications on Pure and Applied Mathematics 59, 797–829 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, L., Xiao, B., Wang, C. (2010). Sparse Representation Based on K-Nearest Neighbor Classifier for Degraded Chinese Character Recognition. In: Qiu, G., Lam, K.M., Kiya, H., Xue, XY., Kuo, CC.J., Lew, M.S. (eds) Advances in Multimedia Information Processing - PCM 2010. PCM 2010. Lecture Notes in Computer Science, vol 6298. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15696-0_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-15696-0_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15695-3
Online ISBN: 978-3-642-15696-0
eBook Packages: Computer ScienceComputer Science (R0)