Noya García, Ernesto; Benedí Ruiz, José Miguel; Sánchez Peiró, Joan Andreu; Anitei, Dan(Springer-Verlag, 2023-04-18)
[EN] We present a discriminative learning algorithm for the probabilistic estimation of two-dimensional probabilistic context-free grammars (2D-PCFG) for mathematical expressions recognition and retrieval. This algorithm ...
Noya, Ernesto; Sánchez Peiró, Joan Andreu; Benedí Ruiz, José Miguel(IEEE, 2021-01-15)
[EN] We consider hypergraphs as a tool obtained with bidimensional Probabilistic Context-Free Grammars to compactly represent the result of the n-best parse trees for an input image that represents a mathematical expression. ...
Noya García, Ernesto(Universitat Politècnica de València, 2020-09-04)
[ES] En la actualidad existen grandes bases de datos de documentos
científicos impresos digitalizados, muchos de los cuales incluyen
expresiones matemáticas. La búsqueda de información textual en
estos documentos ...
Noya García, Ernesto(Universitat Politècnica de València, 2015-10-06)
[ES] El aumento de libros manuscritos digitalizados, y la falta de herramientas precisas para
clasificarlos, ha motivado la creación de un consorcio de universidades europeas bajo el
cual la universidad politécnica de ...
[EN] Keyword spotting techniques are becoming cost-effective solutions for information retrieval in handwritten documents. We explore the extension of the single-word, line-level probabilistic indexing approach described ...
Anitei, Dan; Sánchez Peiró, Joan Andreu; Benedí Ruiz, José Miguel; Noya García, Ernesto(Elsevier, 2023-08)
[EN] Searching for information in printed scientific documents is a challenging problem that has recently received special attention from the Pattern Recognition research community. Mathematical expressions are complex ...