[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
article

A knowledge-based recognition system for historical Mongolian documents

Published: 01 September 2016 Publication History

Abstract

This paper proposes a knowledge-based system to recognize historical Mongolian documents in which the words exhibit remarkable variation and character overlapping. According to the characteristics of Mongolian word formation, the system combines a holistic scheme and a segmentation-based scheme for word recognition. Several types of words and isolated suffixes that cannot be segmented into glyph-units or do not require segmentation are recognized using the holistic scheme. The remaining words are recognized using the segmentation-based scheme, which is the focus of this paper. We exploit the knowledge of the glyph characteristics to segment words into glyph-units in the segmentation-based scheme. Convolutional neural networks are employed not only for word recognition in the holistic scheme, but also for glyph-unit recognition in the segmentation-based scheme. Based on the analysis of recognition errors in the segmentation-based scheme, the system is enhanced by integrating three strategies into glyph-unit recognition. These strategies involve incorporating baseline information, glyph-unit grouping, and recognizing under-segmented and over-segmented fragments. The proposed system achieves 80.86 % word accuracy on the Mongolian Kanjur test samples.

References

[1]
Li, W., Gao, G., Hou, H., Li, Z.: A design and implementation of element segmentation in the recognition of printed mongolian characters. J. Inn. Mong. Univ. 34(3), 357---360 (2003)
[2]
Wei, H.: Study of key techniques in the printed mongolian character recognition. Ph.D. thesis (2006)
[3]
Wei, H., Gao, G.: Machine-printed traditional mongolian characters recognition using bp neural networks. In: Proceedings of the International Conference on Computational Intelligence and Software Engineering (CiSE), pp. 1---7 (2009)
[4]
Peng, L., Liu, C., Ding, X., Jin, J., Wu, Y., Wang, H., Bao, Y.: Multi-font printed mongolian document recognition system. Int. J. Doc. Anal. Recognit. 13(2), 93---106 (2010)
[5]
Gao, G., Su, X., Wei, H., Gong, Y.: Classical mongolian words recognition in historical document. In: Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR), pp. 692---697. IEEE Computer Society (2011)
[6]
Wei, H., Gao, G.: A keyword retrieval system for historical mongolian document images. Int. J. Doc. Anal. Recognit. 17(1), 33---45 (2014)
[7]
Quejingzabu.: Mongolian Unicode. Inner Mongolia University Press, Hohhot (2000)
[8]
Aghbari, Z.A., Brook, S.: Hah manuscripts: a holistic paradigm for classifying and retrieving historical arabic handwritten documents. Expert Syst. Appl. 36(8), 10942---10951 (2009)
[9]
Sagheer, M.W., He, C.L., Nobile, N., Suen, C.Y.: Holistic urdu handwritten word recognition using support vector machine. In: Proceedings of the 20th International Conference on Pattern Recognition (ICPR), pp. 1900---1903 (2010)
[10]
Ding, X., Liu, H.: Segmentation-driven offline handwritten chinese and arabic script recognition. In: Doermann, D., Jaeger, S. (eds.) Proceedings of the 2006 Conference on Arabic and Chinese Handwriting Recognition (SACH), pp. 196---217. Springer, Berlin (2006)
[11]
Lee, H., Verma, B.: Binary segmentation algorithm for english cursive handwriting recognition. Pattern Recognit. 45(4), 1306---1317 (2012)
[12]
Zand, M., Nilchi, A.N., Monadjemi, S.A.: Recognition-based segmentation in persian character recognition. In: Proceedings of World Academy of Science, Engineering and Technology, vol. 2. pp 162---166 (2008)
[13]
Saba, T., Rehman, A., Elarbi-Boudihir, M.: Methods and strategies on off-line cursive touched characters segmentation: a directional review. Artif. Intell. Rev. 42, 1047---1066 (2014)
[14]
Alginahi, Y.M.: A survey on Arabic character segmentation. Int. J. Doc. Anal. Recognit. 16(2), 105---126 (2013)
[15]
Verma, B., Lee, H.: Segment confidence-based binary segmentation (scbs) for cursive handwritten words. Expert Syst. Appl. 38(9), 11167---11175 (2011)
[16]
Cheng, C.K., Blumenstein, M.: The neural-based segmentation of cursive words using enhanced heuristics. In: Proceedings of the 8th International Conference on Document Analysis and Recognition (ICDAR), vol. 2. pp. 650---654 (2005)
[17]
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62---66 (1979)
[18]
Sermanet, P., Chintala, S., LeCun, Y.: Convolutional neural networks applied to house numbers digit classification. In: International Conference on Pattern Recognition (ICPR), pp. 3288---3291 (2012)
[19]
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106---1114 (2012)
[20]
Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. Adv. Neural Inf. Process. Syst. 26, 2553---2561 (2013)
[21]
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: International Conference on Learning Representations (ICLR) (2014)
[22]
Kim, H.J., Lee, J.S., Yang, H.S.: Human action recognition using a modified convolutional neural network. In: the 4th International Symposium on Neural Networks (ISNN), pp. 715---723 (2007)
[23]
Indermuhle, E., Liwicki, M., Bunke, H.: Recognition of handwritten historical documents: Hmm-adaptation versus writer specific training. In: Proceedings of the 11th International Conference on Frontiers in Handwriting Recognition (2008)
[24]
Vinciarelli, A., Bengio, S.: Writer adaptation techniques in hmm based off-line cursive script recognition. Pattern Recognit. Lett. 23(8), 905---916 (2002)
[25]
Palm, R.B.: Prediction as a candidate for learning deep hierarchical models of data. Master (2012)
[26]
Tian, X., Zhang, Y.: Segmentation of touching characters in mathematical expressions using contour feature technique. In: Proceedings of the 8th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD), vol. 1. pp. 206---209 (2007)
[27]
Xu, L., Yin, F., Liu, C.L.: Touching character splitting of chinese handwriting using contour analysis and dtw. In: Proceedings of 2010 Chinese Conference on Pattern Recognition (CCPR), pp. 1---5 (2010)
[28]
Ramer, U.: An iterative procedure for the polygonal approximation of plane curves. Comput. Graph. Image Process. 1(3), 244---256 (1972)
[29]
Douglas, D., Peucker, T.: Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartogr. Int. J. Geogr. Inf. Geovis. 10(2), 112---122 (1973)
[30]
Xiao, X., Leedham, G.: Knowledge-based english cursive script segmentation. Pattern Recognit. Lett. 21(10), 945---954 (2000)
[31]
Sulong, G., Rehman, A., Saba, T.: Improved offline connected script recognition based on hybrid strategy. Int. J. Eng. Sci. Technol. 2(6), 1603---1611 (2010)

Cited By

View all

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image International Journal on Document Analysis and Recognition
International Journal on Document Analysis and Recognition  Volume 19, Issue 3
September 2016
93 pages
ISSN:1433-2833
EISSN:1433-2825
Issue’s Table of Contents

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 01 September 2016

Author Tags

  1. Convolutional neural network
  2. Historical Mongolian document
  3. Holistic recognition
  4. Knowledge-based strategy
  5. Optical character recognition
  6. Segmentation-based recognition

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 20 Dec 2024

Other Metrics

Citations

Cited By

View all
  • (2024)Segmentation-Free Todo Mongolian OCR and its Public DatasetPattern Recognition and Computer Vision10.1007/978-981-97-8511-7_6(72-85)Online publication date: 18-Oct-2024
  • (2024)A Multi-feature Fusion Approach for Words Recognition of Ancient Mongolian DocumentsPattern Recognition and Computer Vision10.1007/978-981-97-8511-7_24(334-347)Online publication date: 18-Oct-2024
  • (2023)A hybrid strategy to extract metadata from scholarly articles by utilizing support vector machine and heuristicsScientometrics10.1007/s11192-023-04774-7128:8(4349-4382)Online publication date: 1-Aug-2023
  • (2022)An end-to-end network for irregular printed Mongolian recognitionInternational Journal on Document Analysis and Recognition10.1007/s10032-021-00388-y25:1(41-50)Online publication date: 1-Mar-2022
  • (2021)Data Augmentation Based on CycleGAN for Improving Woodblock-Printing Mongolian Words RecognitionDocument Analysis and Recognition – ICDAR 202110.1007/978-3-030-86337-1_35(526-537)Online publication date: 5-Sep-2021
  • (2019)End-to-End Model for Offline Handwritten Mongolian Word RecognitionNatural Language Processing and Chinese Computing10.1007/978-3-030-32236-6_19(220-230)Online publication date: 9-Oct-2019

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media