This chapter addresses the problem of layout and logical structure extraction from image documents. Two classes of approaches are first studied and discussed in general terms: data-driven and model-driven. In the latter, some specific approaches like rule-based or formal grammar are usually studied on very stereotyped documents providing honest results, while in the former artificial neural networks are often considered for small patterns with good results. Our understanding of these techniques let us to believe that a hybrid model is a more appropriate solution for structure extraction. Based on this standpoint, we proposed a Perceptive Neural Network based approach using a static topology that possesses the characteristics of a dynamic neural network. Thanks to its transparency, it allows a better representation of the model elements and the relationships between the logical and the physical components. Furthermore, it possesses perceptive cycles providing some capacities in data refinement and correction. Tested on several kinds of documents, the results are better than those of a static Multilayer Perceptron.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Marinai, S., Gori, M., Soda, G.: Artificial neural networks for document analysis and recognition. Pattern Analysis And Machine Intelligence 27(1) (2005) 23-35
Chi, Z., Wong, K.: A two-stage binarization approach for document images. In-ternational Symposium on Intelligent Multimadia, Video and Speech Processing (2001) 275-278
Hamza, H., Smigiel, E., Belaïd, A.: Neural based binarization techniques. Inter- national Conference on Document Analysis and Recognition 4(8) (2005) 317-321
Whichello, A.P., Yan, H.: Linking broken character borders with variable sized mask to improve recognition. Pattern Recognition 29(8) (1995) 1429-1435
Le Cun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11) (1998) 2278-2324
Cecotti, H., Belaïd, A.: Rejection strategy for convolutional neural network by adaptive topology applied to handwritten digits recognition. International Con-ference on Document Analysis and Recognition (8) (2005) 765-769
Garris, M.D., Wilson, C.L., Blue, J.L.: Neural network-based systems for hand-print ocr applications. IEEE Transactions on Image Processing 7(8) (1998) 1097-1112
Mao, S., Rosenfeld, A., Kanungo, T.: Document structure analysis algorithms: A literature survey. SPIE Electronic Imaging 50(10) (2003) 197-207
Brugger, R., Zramdini, A., Ingold, R.: Modeling documents for structure recog-nition using generalized n-grams. International Conference on Document Anal-ysis and Recognition 1(4) (1997) 56-60
Hu, T., Ingold, R.: A mixed approach toward an efficient logical structure recog-nition from document images. Electronic Publishing: Origination, Dissemina-tion, and Design 6(4) (1993) 457-468
Niyogi, D., Srihari, S.N.: Knowledge-based derivation of document logical struc-ture. Third International Conference on Document Analysis and Recognition 1 (1995) 472-475
Rangoni, Y., Belaïd, A.: Document logical structure analysis based on perceptive cycles. Document Analysis Systems 1(7) (2006) 117-128
Küchler, A., Goller, C.: Inductive learning in symbolic domains using structure-driven recurrent neural networks. Lecture Notes in Computer Science (1137) (1996) 183-197
Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Transactions on Neural Networks 8(3) (1997) 714-735
Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the theory of neural com-putation. Addison Wesley (1991)
Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Computation (1) (1989) 281-294
Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical sys- tems using neural networks. IEEE Transactions on Neural Networks 1(1) (1990) 4-27
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America 79(8) (1982) 2554-2558
Pineda, F.J.: Dynamics and architecture for neural computation. Journal of Complexity 4(3) (1988) 216-245
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1(2) (1989) 270-280
Sperduti, A., Starita, A., Goller, C.: Learning distributed representations for the classification of terms. Proceedings of International Joint Conference on Artificial Intelligence 1(40) (1995) 509-515
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. Ad- vances in Neural Information Processing Systems 2 (1990) 524-532
Côté, M., Lecolinet, E., Cheriet, M., Suen, C.: Automatic reading of cursive scripts using a reading model and perceptual concepts. the Perceptro system. International Journal on Document Analysis and Recognition 1(1) (1998) 3-17
McClelland, J., Rumelhart, D.: An interactive activation model of context effects in letter perception. Psychological Review (88) (1981) 375-407 Structure Extraction in Printed Documents Using Neural Approaches
Maddouri, S.S., Amiri, H., Belaïd, A.: Local normalization towards global recog- nition of arabic handwritten script. Document Analysis and Systems (2000)
Vajda, S., Rangoni, Y., Cecotti, H., Belaïd, A., A.: A fast learning strategy us- ing data selection for feedforward neural networks. International Workshop on Frontiers in Handwriting Recognition (10) (2006)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Jour-nal of Machine Learning Research (3) (2003) 1157-1182
Nagy, G.: Twenty years of document image analysis in PAMI. Pattern Analysis and Machine Intelligenc 22(1) (2000) 38-62
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Belaïd, A., Rangoni, Y. (2008). Structure Extraction in Printed Documents Using Neural Approaches. In: Marinai, S., Fujisawa, H. (eds) Machine Learning in Document Analysis and Recognition. Studies in Computational Intelligence, vol 90. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76280-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-540-76280-5_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76279-9
Online ISBN: 978-3-540-76280-5
eBook Packages: EngineeringEngineering (R0)