Detalhes bibliográficos
Ano de defesa: |
2016 |
Autor(a) principal: |
Fernandes Junior, Jovan de Andrade
 |
Orientador(a): |
Matos, Leonardo Nogueira |
Banca de defesa: |
Não Informado pela instituição |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade Federal de Sergipe
|
Programa de Pós-Graduação: |
Pós-Graduação em Ciência da Computação
|
Departamento: |
Não Informado pela instituição
|
País: |
Brasil
|
Palavras-chave em Português: |
|
Área do conhecimento CNPq: |
|
Link de acesso: |
https://ri.ufs.br/handle/riufs/3395
|
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. |