RiuNet UPV Home
:
Browsing by Author

Search RiuNet

Browse

All of RiuNet

My Account

RiuNet Help

Admin. UPV

Browsing by Author "Vidal Ruiz, Enrique"

Now showing items 1-20 of 48

A Probabilistic Formulation of Keyword Spotting

Puigcerver I Pérez, Joan (Universitat Politècnica de València, 2019-02-18)

[ES] La detección de palabras clave (Keyword Spotting, en inglés), aplicada a documentos de texto manuscrito, tiene como objetivo recuperar los documentos, o partes de ellos, que sean relevantes para una cierta consulta ...
A Set of Benchmarks for Handwritten Text Recognition on Historical Documents

Sánchez Peiró, Joan Andreu; Romero, Verónica; Toselli, Alejandro Héctor; Villegas, Mauricio; Vidal, Enrique (Elsevier, 2019-10)

[EN] Handwritten Text Recognition is a important requirement in order to make visible the contents of the myriads of historical documents residing in public and private archives and libraries world wide. Automatic Handwritten ...
A Web-Based Demo to Interactive Multimodal Transcription of Historic Text images

Romero Gómez, Verónica; Leiva Torres, Luis Alberto; Alabau Gonzalvo, Vicente; Toselli, Alejandro Héctor; Vidal Ruiz, Enrique (Springer Verlag (Germany), 2009)

[EN] Paleography experts spend many hours transcribing historic documents, and state-of-the-art handwritten text recognition systems are not suitable for performing this task automatically. In this paper we present the ...
A word-based naïve bayes classifier for confidence estimation in speech recognition

Sanchis Navarro, José Alberto; Juan Císcar, Alfonso; Vidal, Enrique (Institute of Electrical and Electronics Engineers (IEEE), 2012-02)

Confidence estimation has been largely used in speech recognition to detect words in the recognized sentence that have been likely misrecognized. Confidence estimation can be seen as a conventional pattern classification ...
Advances in Document Layout Analysis

Bosch Campos, Vicente (Universitat Politècnica de València, 2020-03-05)

[EN] Handwritten Text Segmentation (HTS) is a task within the Document Layout Analysis field that aims to detect and extract the different page regions of interest found in handwritten documents. HTS remains an active ...
Análisis de Maquetación ("Layout") en imágenes de texto manuscrito mediante Redes Neuronales

Prieto Fontcuberta, José Ramón (Universitat Politècnica de València, 2019-10-30)

[ES] Existen grandes colecciones de manuscritos, las cuales contienen información muy valiosa sobre aspectos cruciales de la historia de nuestra sociedad. Existe tal cantidad de documentos que de forma manual se tardarían ...
Aportaciones al reconocimiento automático de texto manuscrito

Pastor Gadea, Moisés (Universitat Politècnica de València, 2008-05-06)

En esta tesis se estudia el problema de la robustez en los sistemas de reconocimiento automático de texto manuscrito off-line. Los sistemas de reconocimiento automático de texto manuscrito estarán maduros para su uso ...
Approximate search for textual information in images of historical manuscripts using simple regular expression queries

Andrés Moreno, José (Universitat Politècnica de València, 2020-09-22)

[ES] Los archivos históricos así como otras instituciones de patrimonio cultural han estado digitalizando sus colecciones de documentos históricos con el fin de hacerlas accesible a través de Internet al público en ...
Character-level interaction in multimodal computer-assisted transcription of text images

Martín-Albo Simón, Daniel; Romero Gómez, Verónica; Toselli ., Alejandro Héctor; Vidal, Enrique (Springer Verlag (Germany), 2011)

To date, automatic handwriting text recognition systems are far from being perfect and heavy human intervention is often required to check and correct the results of such systems. As an alternative, an interactive framework ...
CHARACTER-LEVEL INTERACTIONS IN MULTIMODAL COMPUTER-ASSISTED TRANSCRIPTION OF TEXT IMAGES

Martín-Albo Simón, Daniel (Universitat Politècnica de València, 2011-07-26)

HTR systems don't achieve acceptable results in unconstrained applications. Therefore, it is convenient to use a system that allows the user to cooperate in the most confortable way with the system to generate a correct ...
Clasificación de imágenes de documentos manuscritos a partir de índicesprobabilisticos mediante redes neuronales

Flores Arellano, Juan José (Universitat Politècnica de València, 2021-09-13)

[ES] La clasificación de documentos manuscritos basada en el contenido es una importante tarea que generalmente se realiza en archivos y bibliotecas por expertos con un gran conocimiento sobre el contenido de los documentos. ...
Contex-aware gestures for mixed-initiative text editings UIs

Leiva, Luis A.; Alabau, Vicent; Romero Gómez, Verónica; Toselli, Alejandro Héctor; Vidal, Enrique (Oxford University Press, 2015)

[EN] This work is focused on enhancing highly interactive text-editing applications with gestures. Concretely, we study Computer Assisted Transcription of Text Images (CATTI), a handwriting transcription system that follows ...
Contributions to Pen & Touch Human-Computer Interaction

Martín-Albo Simón, Daniel (Universitat Politècnica de València, 2016-09-01)

[EN] Computers are now present everywhere, but their potential is not fully exploited due to some lack of acceptance. In this thesis, the pen computer paradigm is adopted, whose main idea is to replace all input devices ...
Development and experimentation of a deep learning system for convolutional and recurrent neural networks

Mocholí Calvo, Carlos (Universitat Politècnica de València, 2018-09-11)

[EN] At present, there are very few deep learning toolkits focused on the task of Handwritten Text Recognition (HTR). HTR refers to the problem of recognizing a sequence of characters in an input image. For this reason, ...
Diverse Contributions to Implicit Human-Computer Interaction

Leiva Torres, Luis Alberto (Universitat Politècnica de València, 2012-11-13)

Cuando las personas interactúan con los ordenadores, hay mucha información que no se proporciona a propósito. Mediante el estudio de estas interacciones implícitas es posible entender qué características de la interfaz de ...
Document segmentation using Relative Location Features

Cruz Fernández, Francisco (Universitat Politècnica de València, 2013-02-06)

[ES] Presentamos un método genérico para análisis de layout ideado para trabajar sobre documentos con layouts Manhattan y no-Manhattan. Proponemos la combinación de Relative Location Features junto con características ...
Escritoire: A Multi-touch Desk with e-Pen Input for Capture, Management and Multimodal Interactive Transcription of Handwritten Documents

Martín-Albo Simón, Daniel; Romero Gómez, Verónica; Vidal Ruiz, Enrique (Springer, 2015-06)

A large quantity of documents used every day are still handwritten. However, it is interesting to transform each of these documents into its digital version for managing, archiving and sharing. Here we present Escritoire, ...
Exploiting Existing Modern Transcripts for Historical Handwritten Text Recognition

Villegas, Mauricio; Toselli, Alejandro Héctor; Romero Gómez, Verónica; Vidal, Enrique (IEEE, 2016)

[EN] Existing transcripts for historic manuscripts are a very valuable resource for training models useful for automatic recognition, aided transcription, and/or indexing of the remaining untranscribed parts of these ...
General Overview of ImageCLEF at the CLEF 2016 Labs

Villegas, Mauricio; Mueller, Henning; Seco de Herrera, Alba Garcia; Schaer, Roger; Bromuri, Stefano; Gilbert, Andrew; Piras, Luca; Wang, Josiah; Yan, Fei; Ramisa, Arnau; Dellandrea, Emmanuel; Gaizauskas, Robert; Mikolajczyk, Krystian; Puigcerver I Pérez, Joan; Toselli, Alejandro Héctor; Sánchez Peiró, Joan Andreu; Vidal Ruiz, Enrique (Springer Verlag (Germany), 2016)

This paper presents an overview of the ImageCLEF 2016 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) labs 2016. ImageCLEF is an ongoing initiative that ...
Ground-Truth production in the tranScriptorium Project

Gatos, Basilis; Louloudis, Georgios; Caser, Tim; Grint, Kris; Romero Gómez, Verónica; Sánchez Peiró, Joan Andreu; Toselli, Alejandro Héctor; Vidal, Enrique (IEEE Computer Society - Conference Publishing Services (CPS), 2014-04-07)

Tran Scriptorium is a 3-years project that aims to develop innovative, cost-effective solutions for the indexing, search and full transcription of historical handwritten document images, using Handwritten Text Recognition ...