A Deep HMM model for multiple keywords spotting in handwritten documentsReportar como inadecuado

A Deep HMM model for multiple keywords spotting in handwritten documents - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 LITIS - Laboratoire d-Informatique, de Traitement de l-Information et des Systèmes

Abstract : In this paper, we propose a query by string word spotting system able to extract arbitrary key-words in handwritten documents, taking both segmen-tation and recognition decisions at the line level. The system relies on the combination of a HMM line model made of keyword and non-keyword filler models, with a deep neural network DNN that estimates the state-dependent observation probabilities. Experiments are carried out on RIMES database, an unconstrained hand-written document database that is used for benchmark-ing different handwriting recognition tasks. The ob-tained results show the superiority of the proposed frame-work over the classical GMM-HMM and standard HMM hybrid architectures.

Keywords : DNN HMM Hidden Markov Models Keyword Spotting Deep neural network Hybrid Deep architecture Handwriting Recognition

Autor: Simon Thomas - Clement Chatelain - Laurent Heutte - Thierry Paquet - Yousri Kessentini -

Fuente: https://hal.archives-ouvertes.fr/


Documentos relacionados