Syntactic Modeling and Recognition of Document Images

Abstract

Abstract. In this work, we propose a new scheme for the recognition of document images under a syntactic approach. We present a new method to model the layout of the document using a tree-like representation of the form. The syntactic representation of the documents are used to infer a tree automaton for each one of the classes involved in the task. An error-correcting analysis of tree languages allows us to carry out the classification. The experimentation carried out showed the good behaviour of the approach: error rate of 1.18%.

Grammatical inference of directed acyclic graph languages with polynomial time complexity

“…Structural information is sometimes enough to successfully solve applied tasks (for instance, document recognition [31]). In order to illustrate that our approach is also suitable in this situation, we modified the samples of Hairpin, GREC and Mutagenicity datasets in order to erase the labels of the internal nodes.…”

“…Looking also to enhance the possibilities of language inference, several works study the task of tree language inference [14,6,23], as well as its application to real tasks [31,36,46,20]. In the grammatical inference framework, when more general graphs are considered, the main problem that arises is computational complexity, and, usually, graphs are reduced to less complex representations (usually some kind of graph traversal).…”