Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. In: International Workshop on Document Analysis Systems, pp. Smigiel, E., Belaid, A., Hamza, H.: Self-organizing maps and ancient documents. Setitra, I., Meziane, A.: Old manuscripts restoration using segmentation. Serra, J., Vincent, L.: An overview of morphological filtering. Rivest-Hénault, D., Moghaddam, R.F., Cheriet, M.: A local linear level set method for the binarization of degraded historical document images. In: 2018 16th International Conference on Frontiers in Handwriting Recognition. Pratikakis, I., Zagoris, K., Barlas, G., Gatos, B.: ICFHR 2018 competition on document image binarization (H-DIBCO 2018). In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. Pratikakis, I., Zagoris, K., Barlas, G., Gatos, B.: ICDAR 2017 competition on document image binarization (DIBCO 2017). Otsu, N.: A threshold selection method from gray-level histograms. In: 2009 17th European Signal Processing Conference, pp. Mohamed, O.M.M., Jaïdane-Saïdane, M.: Generalized Gaussian mixture model. Moghaddam, R.F., Cheriet, M.: RSLDI: restoration of single-sided low-quality document images. (eds.): Digital Hampi: Preserving Indian Cultural Heritage. Mallik, A., Chaudhury, S., Chandru, V., Srinivasan, S. Garain, U., Paquet, T., Heutte, L.: On foreground-background separation in low quality document images. 39, 1–38 (1977)ĭubois, E., Pathak, A.: Reduction of bleed-through in scanned manuscript documents. Springer, Berlin (2018)ĭempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. (eds.): Heritage Preservation: A Computational Approach. PHI Learning, New Delhi (2010)Ĭhanda, B., Chaudhuri, S., Chaudhury, S. IEEE, Piscataway (2009)Ĭhanda, B., Majumder, D.D.: Digital Image Processing and Analysis, 2nd edn. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009, pp. Keywordsīanerjee, J., Namboodiri, A.M., Jawahar, C.: Contextual restoration of severely degraded document images. It is worth mentioning that these methods can be extended easily for printed degraded documents as well. Hence, the proposed methods are ideally suited for digital heritage preservation repositories where the number of samples is low. Experiments demonstrate that the proposed systems perform well on handwritten document images with severe degradation, even when trained with a small dataset. extracting text with its original colour) are achieved using a deep neural network. Note that a Gaussian mixture model requires setting parameters manually to alleviate this problem, we propose a second approach where both the background reconstruction and the foreground extraction (i.e. The background is then reconstructed based on a Gaussian mixture model. In the first approach, a deep neural network has been used for text extraction from the document image. The ground truth data to train the desired network is generated semi-automatically, involving a pragmatic combination of colour transformation, Gaussian mixture model-based segmentation and correction by using mathematical morphological operators. In addition, a small-scale dataset consisting of images of 26 heritage letters is introduced. This chapter describes two novel methods for the restoration of old, degraded handwritten documents using a deep neural network. Image restoration is a crucial computer vision task.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |