Single sample face recognition from video via stacked supervised auto-encoder

Pedro J.Soto Vega, Raul Queiroz Feitosa, Victor H.Ayma Quirita, Patrick Nigri Happ

Producción científica: Capítulo del libro/informe/acta de congresoArticulo (Contribución a conferencia)revisión exhaustiva

11 Citas (Scopus)

Resumen

This work proposes and evaluates strategies based on Stacked Supervised Auto-Encoders (SSAE) for face representation in video surveillance applications. The study focuses on the identification task with a single sample per person (SSPP) in the gallery. Variations in terms of pose, facial expression, illumination and occlusion are approached in two ways. First, the SSAE extracts features from face images, which are robust to such variations. Second, we propose methods to exploit the multiple samples per persons probes (MSPPP) that can be extracted from video sequences. Three variants of the proposed method are compared upon HONDA/UCSD and VIDTIMIT video datasets. The experimental results demonstrate that strategies combining SSAE and MSPPP are able to outperform other SSPP methods, such a local binary patterns, in face recognition from video.

Idioma originalInglés
Título de la publicación alojadaProceedings - 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas96-103
Número de páginas8
ISBN (versión digital)9781509035687
DOI
EstadoPublicada - 10 ene. 2017
Publicado de forma externa
Evento29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016 - Sao Jose dos Campos, Sao Paulo, Brasil
Duración: 4 oct. 20167 oct. 2016

Serie de la publicación

NombreProceedings - 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016

Conferencia

Conferencia29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016
País/TerritorioBrasil
CiudadSao Jose dos Campos, Sao Paulo
Período4/10/167/10/16

Huella

Profundice en los temas de investigación de 'Single sample face recognition from video via stacked supervised auto-encoder'. En conjunto forman una huella única.

Citar esto