Introduction of statistical information in a syntactic analyzer for document image recognition

André O. Maroneze; Bertrand Coüasnon; Aurélie Lemaitre

doi:10.1117/12.873393

Translator Disclaimer

24 January 2011 Introduction of statistical information in a syntactic analyzer for document image recognition

André O. Maroneze; Bertrand Coüasnon; Aurélie Lemaitre

Author Affiliations +

Proceedings Volume 7874, Document Recognition and Retrieval XVIII; 787404 (2011) https://doi.org/10.1117/12.873393
Event: IS&T/SPIE Electronic Imaging, 2011, San Francisco Airport, California, United States

Abstract

This paper presents an improvement to a document layout analysis system, offering a possible solution to Sayre's paradox ("a letter must be recognized before it can be segmented; and it must be segmented before it can be recognized"). This improvement, based on stochastic parsing, allows integration of statistical information, obtained from recognizers, during syntactic layout analysis. We present how this fusion of numeric and symbolic information in a feedback loop can be applied to syntactic methods to simplify document description. To limit combinatorial explosion during exploration of solutions, we devised an operator that allows optional activation of the stochastic parsing mechanism. Our evaluation on 1250 handwritten business letters shows this method allows the improvement of global recognition scores.

Citation Download Citation

André O. Maroneze, Bertrand Coüasnon, and Aurélie Lemaitre "Introduction of statistical information in a syntactic analyzer for document image recognition", Proc. SPIE 7874, Document Recognition and Retrieval XVIII, 787404 (24 January 2011); https://doi.org/10.1117/12.873393

ACCESS THE FULL ARTICLE