A tracking framework for accurate face localization

This paper proposes a complete framework for accurate face localization on video frames. Detection and forward tracking are first combined according to predefined rules to get a first set of face candidates. Backward tracking is then applied to provide another set of possible localizations. Finally...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pitas, Ioannis, Cherif, Ines, Solachidis, Vassilios
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2006
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23951
Aporte de:
Descripción
Sumario:This paper proposes a complete framework for accurate face localization on video frames. Detection and forward tracking are first combined according to predefined rules to get a first set of face candidates. Backward tracking is then applied to provide another set of possible localizations. Finally a dynamic programming algorithm is used to select the candidates that minimize a specific cost function. This method was designed to handle different scale, pose and lighting conditions. The experiments show that it improves the face detection rate compared to a frame-based detector and provides a higher precision than a forward information-based tracker.