A structural classifier to automatically identify form classes
This article deals with the description of a new classifier for an automatic form class identification system. This new structural classifier is based on a tree comparisons. The high level information used by this classifier is presented in the article. A module first extracts the form content. The form content organisation is described in a hierarchical way modelled by a tree. This tree corresponds to the input features of the structural classifier. Experimental results are presented and several strategies of combined uses of this structural classifier with other classical classifiers are suggested in order to enhance the results.
Unable to display preview. Download preview PDF.
- 1.Diana S., Trupin E., Lecourtier Y., Labiche J.: An Assistant to the Modelisation of Forms. MultiMedia Signal Processing Princeton NJ USA (1997) 163–168Google Scholar
- 2.Diana S., Trupin E., Lecourtier Y., Labiche J.: From Acquisition to Modelisation of a Form Base to Retrieve Information. International Conference on Document Analysis and Recognition Ulm Germany (1997) 762–765Google Scholar
- 4.Rumelhart D.E, McClellard J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Foundations, The MIT Press Vol 1 (1986)Google Scholar
- 5.Miclet L.: Méthodes structurelles pour la reconnaissance des formes. (ed.): Eyrolles (1984)Google Scholar
- 6.Ishitani Y.: Model Matching Based on Association Graph for Form Image Understanding.. International Conference on Document Analysis and Recongnition Montreal Canada (1995) 287–292Google Scholar
- 7.Budin A.: On The Problem of Attributed Relational Graph Matching. Automatika 33 (1992) 151–157Google Scholar
- 8.Thomasson M.G.:, Gonzalez R.C: Syntactic Recognition of Imperfectly Specific Patterns. IEEE Trans. on Computers Vol.24 1 (1975) 93–96Google Scholar