Reconhecimento automático de expressões faciais baseado em características geométricas

In recent years we have seen great advances in Computer Vision research area that have made possible change the we interact with machines. To achieve an effective Intelligent Human-Computer Interface (IHC), in addition to recognize body movements or vocal commands, it is necessary the machine be abl...

ver descrição completa

Detalhes bibliográficos
Autor: Fernandes Junior, Jovan de Andrade
Formato: tesis de maestría
Estado:Versión publicada
Fecha de publicación:2016
País:Brasil
Recursos:Universidade Federal de Sergipe (UFS)
Repositorio:Repositório Institucional da UFS
Idioma:portugués
OAI Identifier:oai:oai:ri.ufs.br:repo_01:riufs/3395
Acesso em linha:https://ri.ufs.br/handle/riufs/3395
Access Level:acceso abierto
Palavra-chave:Computação
Programas de computador
Desenvolvimento de software
Tecnologia da informação
Reconhecimento de padrões
Sistemas de reconhecimento de padrões
Face
Geometria facial
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
Descrição
Resumo:In recent years we have seen great advances in Computer Vision research area that have made possible change the we interact with machines. To achieve an effective Intelligent Human-Computer Interface (IHC), in addition to recognize body movements or vocal commands, it is necessary the machine be able to understand human facial expressions. Although there are several publications that aims to recognize facial expressions, this task is not yet performed by a machine with the same efficiency as the human being. This work proposes two geometric-based feature selection approaches for facial expression recognition. The first, called Empirical Distances method obtained 77.66% of recognition rate. The second, called CFS Distances method, obtained 91.33% of recognition rate. The results obtained are compatible with the state of the art in this research area.