Abstract
We approach the analysis of electronic documents as a multi-stage process, which we implement via a multi-filter document processing framework that provides (a) flexibility for research prototyping, (b) efficiency for development, and (c) reliability for deployment. In the context of this framework, we present our multi-stage solutions to multi-engine Arabic OCR (MEMOE) and Arabic handwriting recognition (AHWR). We also describe our adaptive pre-OCR document image cleanup system called ImageRefiner. Experimental results are reported for all mentioned systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
AbdulKader, A.: A two tier Arabic handwriting recognition based on conditional joining rules. In: Proceedings of the Summit on Arabic and Chinese Handwriting, pp. 121–128 (2006)
Al-Ani, A., Deriche, M.: A new technique for combining multiple classifiers using the Dempster–Shafer theory of evidence. J. Artif. Intell. Res. 17, 333–361 (2002)
Alma’adeed, S., Higgins, C., Elliman, D.: Off-line recognition of handwritten Arabic words using multiple Hidden Markov Models. In: Twenty-third SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, vol. 17, pp. 75–79 (2004)
Borovikov, E., Zavorin, I., Turner, M.: A filter based post-OCR accuracy boost system. In: Proceedings of the 1st ACM Workshop on Hardcopy Document Processing (2004)
Cannon, M., Hochberg, J., Kelly, P.: Quality assessment and restoration of typewritten document images. Int. J. Doc. Anal. Recognit. 2(2–3), 80–89 (1999)
Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley-Interscience, New York (1973)
El Abed, H., Märgner, V.: Comparison of combination methods of Arabic handwritten word recognizers. In: 5th International Multi-Conference on Systems, Signals and Devices, pp. 1–6 (2008)
Essoukri, N., Amara, B., Bouslama, F.: Classification of Arabic script using multiple sources of information: State of the art and perspectives. Int. J. Doc. Anal. Recognit. 5(4), 195–212 (2003)
Farah, N., Souici, L., Sellami, M.: Classifiers combination and syntax analysis for Arabic literal amount recognition. Eng. Appl. Artif. Intell. 19(1), 29–39 (2006)
Govindaraju, V.: Paradigms in handwriting recognition. In: Proceedings of the Summit on Arabic and Chinese Handwriting, pp. 171–175 (2006)
Ho, T.K.: Multiple classifier combination: Lessons and next steps. In: Bunke, H., Kandel, A. (eds.) Hybrid Methods in Pattern Recognition, pp. 171–198. World Scientific, Singapore (2002)
Jaeger, S.: Informational classifier fusion. In: Proceedings of the International Conference on Pattern Recognition, vol. I, pp. 216–219 (2004)
Klein, S.T., Kopel, M.: A voting system for automatic OCR correction. In: Proceedings of the SIGIR 2002 Workshop on Information Retrieval and OCR: From Converting Content to Grasping Meaning, University of Tampere, August 2002
Kolak, O., Resnik, P., Byrne, W.: A generative probabilistic OCR model for NLP applications. In: Proceedings of HLT-NAACL, May 2003
Kuncheva, L.: Combining Pattern Classifiers. Methods and Algorithms. Wiley, New York (2004)
Lee, D.-S.: A theory of classifier combination: the neural network approach. Ph.D. thesis, State University of New York at Buffalo (1995)
Lin, X.: Reliable OCR solution for digital content re-mastering. In: Proceedings of SPIE Conference on Document Recognition and Retrieval IX (2002)
Lin, X.: DRR research beyond COTS OCR software: A survey. Technical Report HPL-2004-167, Imaging Systems Laboratory, HP Laboratories Palo Alto, CA (2004)
Lorigo, L.M.: Arabic handwriting recognition and application to ancient documents. In: Proceedings of the Summit on Arabic and Chinese Handwriting, pp. 111–120 (2006)
Lorigo, L.M., Govindaraju, V.: Off-line Arabic handwriting recognition: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 28(5), 712–724 (2006)
Märgner, V., Pechwitz, M., El-Abed, H.: ICDAR 2005 Arabic handwriting recognition competition. In: Proceedings of the International Conference on Document Analysis and Recognition, Seoul, Korea, pp. 70–74 (2005)
McNamara, J., Casey, D., Smith, R., Bradburn, D.: A classifier for evaluating the effects of image processing on character recognition. In: Image Algebra and Morphological Image Processing, pp. 109–120 (1993)
Nartker, T.A., Rice, S.V., Lumos, S.E.: Software tools and test data for research and testing of page-reading OCR systems. In: SPIE Conference Document Recognition and Retrieval, San Jose, CA, January 2005, vol. 5676, pp. 37–47 (2005)
Niblack, W.: An Introduction to Image Processing. Prentice-Hall, Englewood Cliffs (1996)
Nomoto, T.: Predictive models of performance in multi-engine machine translation. In: MT Summit IX, pp. 269–276 (2003)
Otsu, N.: A threshold selection method for gray level histograms. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)
Parker, J.R.: Algorithms for Image Processing and Computer Vision. Wiley, New York (1996)
Pechwitz, M., Snoussi Maddouri, S., Märgner, V., Ellouze, N., Amiri, H.: IFN/ENIT-database of handwritten Arabic words. In: Proceedings of CIFED, pp. 129–136 (2002)
Sezgin, M., Sankur, B.: Survey over image thresholding techniques and quantitative performance evaluation. J. Electron. Imaging 13, 146–165 (2004)
Snoussi Maddouri, S., Amiri, H., Belaïd, A., Choisy, Ch.: Combination of local and global vision modeling for Arabic handwritten words recognition. In: 8th IWFHR, pp. 128–135 (2002)
Summers, K.: Document image improvement for OCR as a classification problem. In: Document Recognition and Retrieval X, vol. 5010 (2003)
Tong, X., Evans, D.A.: A statistical approach to automatic OCR error correction in context. In: 4th Workshop on Very Large Corpora, Copenhagen, Denmark, August 1996, pp. 88–100 (1996)
Yang, Y., Summers, K., Turner, M.: A text image enhancement system based on segmentation and classification methods. In: Proceedings of the 1st ACM Workshop on Hardcopy Document Processing (2004)
Zavorin, I., Borovikov, E.: Data collection and annotation for Arabic document analysis. In: Märgner, V., El Abed, H. (eds.) Guide to OCR for Arabic Scripts. Springer, Berlin (2012)
Zavorin, I., Borovikov, E., Turner, M.: Initial results in offline Arabic handwriting recognition using large-scale geometric features. In: Proceedings of the Symposium on Document Image Understanding Technology, December 2005
Zavorin, I., Borovikov, E., Turner, M., Hernandez, L.: Adaptive pre-OCR cleanup of grayscale document images. In: Proceedings of SPIE/IS&T Electronic Imaging Conference on Document Recognition & Retrieval XIII. SPIE, Bellingham (2006)
Zavorin, I., Borovikov, E., Borovikov, A., Hernandez, L., Summers, K., Turner, M.: A multi-evidence, multi-engine OCR system. In: Proceedings of SPIE/IS&T Electronic Imaging Conference on Document Recognition & Retrieval XIV (2007)
Zavorin, I., Borovikov, E., Davis, E., Borovikov, A., Summers, K.: Combining different classification approaches to improve off-line Arabic handwritten word recognition. In: Proceedings of SPIE/IS&T Electronic Imaging Conference on Document Recognition & Retrieval XV (2008)
Zuo, Y., Zong, C.: Multi-engine based Chinese-to-English translation system. In: The INTERSPEECH/ICSLP-2004 Satellite Workshop: International Workshop on Spoken Language Translation (2004)
Acknowledgements
We would like to express our thanks to David Doermann (UMCP) for providing a nice GUI tool for Arabic handwriting ground truth preparation, Sargur N. Srihari (CEDAR) for providing an efficient solution for document image segmentation, Volker Märgner (TU Braunschweig) for providing access to the IfN database and for evaluating our Arabic handwriting recognizer, Leila Saidi (CACI) for helping with Arabic documents ground truth creation, Ericson Davis (CACI) for providing technical solutions to document image processing, Anna Borovikov (CACI) for coordinating Arabic corpora creation and for mathematical advice, Yaguang Yang (CACI) for providing custom document image transform and for software coding, Kristen Summers (CACI) for providing technical expertise and leadership in the area of document understanding in general and in Arabic OCR in particular, Mark Turner (CACI) for administrative project oversight, and Luis Hernandez (ARL) for access to various Arabic datasets and GOTS software.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag London
About this chapter
Cite this chapter
Borovikov, E., Zavorin, I. (2012). A Multi-stage Approach to Arabic Document Analysis. In: Märgner, V., El Abed, H. (eds) Guide to OCR for Arabic Scripts. Springer, London. https://doi.org/10.1007/978-1-4471-4072-6_3
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4072-6_3
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4071-9
Online ISBN: 978-1-4471-4072-6
eBook Packages: Computer ScienceComputer Science (R0)