论文信息 - Analysis and conversion of documents

Analysis and conversion of documents

This paper deals with the use of grammatical formalisms to recognise the physical and the logical structures of a composite document. We propose a new system based on W-grammar for document analysis and conversions. As an application the system identifies printed "summaries" and converts them into machine readable form such as the hypertext markup language (HTML) which is handled by Navigator software.

Hubert Emptoz | Alexandre S. Saidi | Souad Tayeb-bey

[1] Mahesh Viswanathan,et al. A prototype document image analysis system for technical journals , 1992, Computer.

[2] Friedrich M. Wahl,et al. Document Analysis System , 1982, IBM J. Res. Dev..

[3] Heikki Mannila,et al. Forming Grammars for Structured Documents: an Application of Grammatical Inference , 1994, ICGI.

[4] Yannick Chenevoy. Reconnaissance structurelle de documents imprimés : études et réalisations , 1992 .

[5] Abdel Belaïd,et al. Knowledge-Based System for Structured Document Recognition , 1990, MVA.

[6] Marc Richetin,et al. Efficient regular grammatical inference for pattern recognition , 1984, Pattern Recognit..

[7] Jeffrey D. Ullman,et al. Introduction to Automata Theory, Languages and Computation , 1979 .

[8] Alexandre S. Saidi,et al. Grammatical Formalism for Document Understanding System: From Documents towards HTML Text , 1997, BSDIA.

[9] Sadegh Saïdi. Extensions grammaticales de la programmation (en) logique : Application à la validation des grammaires affixes , 1992 .

[10] Francisco Casacuberta,et al. Local Languages, the Succesor Method, and a Step Towards a General Methodology for the Inference of Regular Grammars , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.