Fusion of holistic and part based features for gender classification in the wild

Gender classi cation (GC) in the wild is an active area of current research. In this paper, we focus on the combination of a holistic state of the art approach based on features extracted from the facial pattern, with patch based approaches that focus on inner facial areas. Those regions are selecte...

Descripción completa

Detalles Bibliográficos
Autores: Castrillón-Santana, Modesto, Lorenzo-Navarro, Javier, Ramón-Balmaseda, Enrique
Tipo de recurso: capítulo de libro
Fecha de publicación:2015
País:España
Repositorio:accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canaria
OAI Identifier:oai:accedacris.ulpgc.es:10553/20096
Acceso en línea:http://hdl.handle.net/10553/20096
Access Level:acceso abierto
Palabra clave:120304 Inteligencia artificial
Recognition
Patterns
Gender classification
Local descriptors
Score level fusion
Descripción
Sumario:Gender classi cation (GC) in the wild is an active area of current research. In this paper, we focus on the combination of a holistic state of the art approach based on features extracted from the facial pattern, with patch based approaches that focus on inner facial areas. Those regions are selected for being relevant to the human system according to the psychophysics literature: the ocular and the mouth areas. The resulting proposed GC system outperforms previous approaches, reducing the classi cation error of the holistic approach roughly a 30%.