Facial expression recognition using shape and texture information

A novel method based on shape and texture information is proposed in this paper for facial expression recognition from video sequences. The Discriminant Non-negative Matrix Factorization (DNMF) algorithm is applied at the image corresponding to the greatest intensity of the facial expression (last f...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pitas, Ioannis, Kotsia, Irene
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2006
Materias:
Ciencias Informáticas
Algorithms
Support Vector Machines (SVMs) system
Shape
Texture
Graphics recognition and interpretation
Discriminant Non-negative Matrix Factorization (DNMF) algorithm
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23944
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23944
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Algorithms
Support Vector Machines (SVMs) system
Shape
Texture
Graphics recognition and interpretation
Discriminant Non-negative Matrix Factorization (DNMF) algorithm
spellingShingle Ciencias Informáticas
Algorithms
Support Vector Machines (SVMs) system
Shape
Texture
Graphics recognition and interpretation
Discriminant Non-negative Matrix Factorization (DNMF) algorithm
Pitas, Ioannis
Kotsia, Irene
Facial expression recognition using shape and texture information
topic_facet Ciencias Informáticas
Algorithms
Support Vector Machines (SVMs) system
Shape
Texture
Graphics recognition and interpretation
Discriminant Non-negative Matrix Factorization (DNMF) algorithm
description A novel method based on shape and texture information is proposed in this paper for facial expression recognition from video sequences. The Discriminant Non-negative Matrix Factorization (DNMF) algorithm is applied at the image corresponding to the greatest intensity of the facial expression (last frame of the video sequence), extracting that way the texture information. A Support Vector Machines (SVMs) system is used for the classi cation of the shape information derived from tracking the Candide grid over the video sequence. The shape information consists of the di erences of the node coordinates between the rst (neutral) and last (fully expressed facial expression) video frame. Subsequently, fusion of texture and shape information obtained is performed using Radial Basis Function (RBF) Neural Networks (NNs). The accuracy achieved is equal to 98,2% when recognizing the six basic facial expressions
format Objeto de conferencia
Objeto de conferencia
author Pitas, Ioannis
Kotsia, Irene
author_facet Pitas, Ioannis
Kotsia, Irene
author_sort Pitas, Ioannis
title Facial expression recognition using shape and texture information
title_short Facial expression recognition using shape and texture information
title_full Facial expression recognition using shape and texture information
title_fullStr Facial expression recognition using shape and texture information
title_full_unstemmed Facial expression recognition using shape and texture information
title_sort facial expression recognition using shape and texture information
publishDate 2006
url http://sedici.unlp.edu.ar/handle/10915/23944
work_keys_str_mv AT pitasioannis facialexpressionrecognitionusingshapeandtextureinformation
AT kotsiairene facialexpressionrecognitionusingshapeandtextureinformation
bdutipo_str Repositorios
_version_ 1764820466419105793

Ejemplares similares