Abstract
A paper document processing system is an information system component which transforms information on printed or handwritten documents into a computer-revisable form. In intelligent systems for paper document processing this information capture process is based on knowledge of the specific layout and logical structures of the documents. This article proposes the application of machine learning techniques to acquire the specific knowledge required by an intelligent document processing system, named WISDOM++, that manages printed documents, such as letters and journals. Knowledge is represented by means of decision trees and first-order rules automatically generated from a set of training documents. In particular, an incremental decision tree learning system is applied for the acquisition of decision trees used for the classification of segmented blocks, while a first-order learning system is applied for the induction of rules used for the layout-based classification and understanding of documents. Issues concerning the incremental induction of decision trees and the handling of both numeric and symbolic data in first-order rule learning are discussed, and the validity of the proposed solutions is empirically evaluated by processing a set of real printed documents.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Altamura, O., Esposito, F., and Malerba, D. (1999).WISDOM++: An Interactive and Adaptive Document Analysis System. In Proc. of the 5th Int. Conf. on Document Analysis and Recognition (pp. 366–369). Los Alamitos: IEEE Computer Society Press.
Bayer, T., Bohnacher, U., and Mogg-Schneider, H. (1994). InforPortLab: An Experimental Document Analysis System. In Proc. of the IAPR Workshop on Document Analysis Systems, Kaiserslautern, Germany.
Bergadano, F. and Bisio, R. (1988). Constructive Learning with Continuous-Valued Attributes. In B. Bouchon, L. Saitta, and R.R. Yager (Eds.), Lecture Notes in Computer Science, Vol. 313: Uncertainty and Intelligent Systems (pp. 54–162). Berlin: Springer-Verlag.
Botta, M. and Giordana, A. (1991). Learning Quantitative Features in a Symbolic Environment. In Z.W. Ras and M. Zemankova (Eds.), Lecture Notes in Artificial Intelligence, Vol. 542: Methodologies for Intelligent Systems (pp. 296–305). Berlin: Springer-Verlag.
Connell, J.H. and Brady,M. (1987). Generating and Generalizing Models of Visual Objects, Artificial Intelligence, 31(2), 159–183.
Dengel, A. and Barth, G. (1989). ANASTASIL: A Hybrid Knowledge-Based System for Document Layout Analysis. In Proc. of the 6th Int. Joint Conf. on Artificial Intelligence (pp. 1249–1254).
De Raedt, L. (1992). Inductive Theory Revision. London: Academic Press.
Dzeroski, S. and Bratko, I. (1996). Applications of Inductive Logic Programming. In L. De Raedt (Ed.), Advances in Inductive Logic Programming (pp. 65–81). Amsterdam: IOS Press.
Esposito, F., Lanza, A., Malerba, D., and Semeraro, G. (1997). Machine Learning for Map Interpretation: An Intelligent Tool for Environmental Planning, Applied Artificial Intelligence: An International Journal, 11(10), 673–696.
Esposito, F., Malerba, D., Semeraro, G., Annese, E., and Scafuro, G. (1990). Empirical Learning Methods for Digitized Document Recognition: An Integrated Approach to Inductive Generalization. In Proc. of the 6th IEEE Conf. on Artificial Intelligence Applications (pp. 37–45). Los Alamitos: IEEE Computer Society Press.
Esposito, F., Malerba, D., and Semeraro, G. (1993). Incorporating Statistical Techniques into Empirical Symbolic Learning Systems. In D.J. Hand (Ed.), Artificial Intelligence Frontiers in Statistics (pp. 168–181). London: Chapman & Hall.
Esposito, F., Malerba, D., and Semeraro, G. (1994). Multistrategy Learning for Document Recognition, Applied Artificial Intelligence, 8(1), 33–84.
Esposito, F., Malerba, D., Semeraro, Fanizzi, N., and Ferilli, S. (1998). Adding Machine Learning and Knowledge Intensive Techniques to a Digital Library Service, International Journal on Digital Libraries, 2(1), 3–19.
Fayyad, U.M. and Irani, K.B. (1992). On the Handling of Continuous-Valued Attributes in Decision Tree Generation. Machine Learning, 8, 87–102.
Fayyad, U., Piatesky-Shapiro, G., and Smyth, P. (1996). From Data Mining to Knowledge Discovery: An Overview. In U. Fayyad, G. Piatesky-Shapiro, P. Smyth, and R. Uthurusamy (Eds.), Advances in Knowledge Discovery and Data Mining (pp. 1–35). AAAI/MIT Press.
Fisher, J.L., Hinds, S.C., and D'Amato, D.P. (1990). A Rule-Based System for Document Image Segmentation. In Proc. of the 10th Int. Conf. on Pattern Recognition (pp. 567–572). Los Alamitos: IEEE Computer Society Press.
Gemello, R., Mana, F., and Saitta, L. (1991). Rigel: An Inductive Learning System, Machine Learning, 6(1), 7–35.
Helft, N. (1987). Inductive Generalization: A Logical Framework. In I. Bratko and N. Lavrac (Eds.), Progress in Machine Learning-Proc. of the EWSL87 (pp. 149–157). London: Sigma Press.
Lavrac, N. and Dzeroski, S. (1994). Inductive Logic Programming: Techniques and Applications. Chichester: Ellis Horwood.
Lavrac, N., Dzeroski, S., and Bratko, I. (1996). Handling Imperfect Data in Inductive Logic Programming. In L. De Raedt (Ed.), Advances in Inductive Logic Programming (pp. 48–64). Amsterdam: IOS Press.
Malerba, D., Semeraro, G., and Bellisari, E. (1995). LEX: A Knowledge-Based System for the Layout Analysis. In Proc. of the 3rd Int. Conf. on the Practical Application of Prolog (pp. 429–443).
Malerba, D., Esposito, F., Semeraro, G., and Caggese, S. (1997a). Handling Continuous Data in Top-Down Induction of First-Order Rules. In M. Lenzerini (Ed.), Lecture Notes in Artificial Intelligence, Vol. 1321: AI*IA 97: Advances in Artificial Intelligence (pp. 24–35). Berlin: Springer-Verlag.
Malerba, D., Esposito, F., Semeraro, G., and De Filippis, L. (1997b). Processing Paper Documents in WISDOM. In M. Lenzerini (Ed.), Lecture Notes in Artificial Intelligence, Vol. 1321: AI*IA 97: Advances in Artificial Intelligence (pp. 439–442). Berlin: Springer-Verlag.
Malerba, D., Semeraro, G., and Esposito, F. (1997c). A Multistrategy Approach to Learning Multiple Dependent Concepts. In C. Taylor and R. Nakhaeizadeh (Eds.), Machine Learning and Statistics: The Interface (pp. 87–106). London: Wiley.
Mitchell, T. (1997). Machine Learning. New York: McGraw Hill.
Nagy, G., Seth, S.C., and Stoddard, S.D. (1992). A Prototype Document Image Analysis System for Technical Journals, IEEE Computer, 25(7), 10–22.
Orkin, M. and Drogin, R. (1990). Vital Statistics. New York: McGraw Hill.
Pagurek, B., Dawes, N., Bourassa, G., Evans, G., and Smithers, P. (1990). Letter Pattern Recognition. In Proc. of the 6th Conf. on Artificial Intelligence Applications (pp. 312–319). Los Alamitos: IEEE Computer Society Press.
Quinlan, J.R. (1993). C4.5: Programs for Machine Learning. San Mateo: Morgan Kaufmann.
Quinlan, J.R. and Cameron-Jones, R.M. (1993). FOIL: A Midterm Report. In P.B. Brazdil (Ed.), Lecture Notes in Artificial Intelligence, Vol. 667: Machine Learning: ECML-93 (pp. 3–20). Berlin: Springer-Verlag.
Tang, Y.Y., Yan, C.D., and Suen, C.Y. (1994). Document Processing for Automatic Knowledge Acquisition, IEEE Trans. on Knowledge and Data Engineering, 6(1), 3–21.
Utgoff, P.E. (1994). An Improved Algorithm for Incremental Induction of Decision Trees. In Proc. of the 11th Int. Conf. on Machine Learning (pp. 318–325). San Francisco: Morgan Kaufmann.
Wang, D. and Srihari, R.N. (1989). Classification of Newspaper Image Blocks Using Texture Analysis, Computer Vision, Graphics, and Image Processing, 47, 327–352.
Wong, K.Y., Casey, R.G., and Wahl, F.M. (1982). Document Analysis System, IBM J. of Research Development, 26(6), 647–656.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Esposito, F., Malerba, D. & Lisi, F.A. Machine Learning for Intelligent Processing of Printed Documents. Journal of Intelligent Information Systems 14, 175–198 (2000). https://doi.org/10.1023/A:1008735902918
Issue Date:
DOI: https://doi.org/10.1023/A:1008735902918