[EN] In this thesis a real application related to the string correction process from an OCR classifier in a form digitizing task is presented. These strings come from a classifier with a given error ratio that implies that ...

An OCR process is often followed by the application of a language model to find the best transformation of an OCR hypothesis into a string compatible with the constraints of the document, field or item under consideration. ...

We use Weighted Finite-State Transducers (WFSTs) to represent the different sources of information available: the initial hypotheses, the possible errors, the constraints imposed by the task (interaction language) and the ...

[ES] Ha sido escaso el trabajo realizado en Trabajos Fin de Grado que se haya dirigido a la formación, aplicando los conocimientos técnicos adquiridos en los estudios universitarios. En particular, el dirigido a la formación ...

A technique is proposed to classify documents based on landmarks, with a reject option.

[ES] La diabetes de tipo 2 (DT2) acelera el deterioro de sistema cardiometabólico, siendo por ello causa indirecta de mortalidad, así como de reducción de la calidad de vida de los pacientes. Se estima que el componente ...

[EN] This paper describes an ensemble feature identification algorithm called SEQENS, and measures its capability to identify the relevant variables in a case-control study using a genetic expression microarray dataset. ...