Bernoulli HMMs at subword level for handwritten word recognition

This paper presents a handwritten word recogniser based on HMMs at subword level (characters) in which state-emission probabilities are governed by multivariate Bernoulli probability functions. This recogniser works directly with raw binary pixels of the image, instead of conventional, real-valued l...

ver descrição completa

Detalhes bibliográficos
Autores: Giménez Pastor, Adrián, Juan, Alfons
Tipo de documento: capítulo de livro
Data de publicação:2009
País:España
Recursos:Universitat Politècnica de València (UPV)
Repositório:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglês
OAI Identifier:oai:riunet.upv.es:10251/51259
Acesso em linha:https://riunet.upv.es/handle/10251/51259
Access Level:Acceso aberto
Palavra-chave:HMM
Subword
Bernoulli
Handwritten word recognition
LENGUAJES Y SISTEMAS INFORMATICOS
Descrição
Resumo:This paper presents a handwritten word recogniser based on HMMs at subword level (characters) in which state-emission probabilities are governed by multivariate Bernoulli probability functions. This recogniser works directly with raw binary pixels of the image, instead of conventional, real-valued local features. A detailed experimentation has been carried out by varying the number of states, and comparing the results with those from a conventional system based on continuous (Gaussian) densities. From this experimentation, it becomes clear that the proposed recogniser is much better than the conventional system