Data categorization for a context return applied to logical document structure recognition
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 297-301 Vol. 1
- https://doi.org/10.1109/icdar.2005.83
Abstract
The purpose of this work is to develop a pattern recognition system simulating the human vision. A transparent neural network, with context returns is used. The context returns consist in using global vision to correct local vision (i.e. input data are corrected according to neural network outputs). In order not to compute all the input features during these context returns, a filter-based method was designed to organize the features in clusters. This allows finding a good subset of input features during each cycle, which reduce the computations. The method interest is shown in the case of logical document structure retrieval.Keywords
This publication has 5 references indexed in Scilit:
- Xed: a new tool for extracting hidden structures from electronic documentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Object detection using feature subset selectionPattern Recognition, 2004
- Address-block extraction by Bayesian rulePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- AIDAS: incremental logical structure discovery in PDF documentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An interactive activation model of context effects in letter perception: I. An account of basic findings.Psychological Review, 1981