Giménez Pastor, Adrián(Universitat Politècnica de València, 2014-06-09)
In last years Hidden Markov Models (HMMs) have received significant attention in the
task off-line handwritten text recognition (HTR). As in automatic speech recognition (ASR),
HMMs are used to model the probability of ...
Del Agua Teba, Miguel Angel; Serrano Martinez Santos, Nicolas; Civera Saiz, Jorge; Juan Císcar, Alfonso(Springer Verlag (Germany), 2012)
[EN] An effective approach to transcribe handwritten text documents is to follow a sequential interactive approach. During the supervision phase, user corrections are incorporated into the system through an ongoing retraining ...
Pérez Muñoz, Ignacio(Universitat Politècnica de València, 2016-05-13)
[EN] The Handwriting Text Recognition (HTR) is principally oriented to re-
cognize text lines, that is, the transcription is realized analyzing each different
line of a text. In this framework the problem is that the ...
[EN] Bernoulli HMMs (BHMMs) have been successfully applied to handwritten text recognition (HTR) tasks such as continuous and isolated handwritten words. BHMMs belong to the generative model family and, hence, are usually ...
Martínez Vargas, Jorge(Universitat Politècnica de València, 2014-03-04)
[EN] This report will cover the development of several graphical tools for ground
truth generation in HTR tasks, specifically for layout analysis, line segmentation,
and transcription, as well as one ad hoc tool needed ...
[EN] Hidden Markov Models (HMMs) are now widely used for off-line handwriting recognition in many lan-
guages. As in speech recognition, they are usually built from shared, embedded HMMs at symbol level,
where state-conditional ...