Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks

This article presents the results of analyzing the behavior of the Cone Curvature shapedescriptor (CC) in the task of recognition of facial expressions in 3D images. The CCdescriptor is a representation of the 3D model computed from a set of waves modelingfor each vertex of a polygon mesh. The 3D Fa...

Descripción completa

Detalles Bibliográficos
Autores Principales: Rodriguez Acevedo, Julián Severiano, Prieto Ortiz, Flavio Augusto
Formato: Artículo (Article)
Lenguaje:Español (Spanish)
Publicado: Universidad Distrital Francisco José de Caldas 2015
Materias:
Acceso en línea:http://hdl.handle.net/11349/19835
id ir-11349-19835
recordtype dspace
spelling ir-11349-198352019-09-19T21:38:59Z Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks Análisis y Comparación del Descriptor Cone Curvature frente al Reconocimiento de Expresiones Faciales Rodriguez Acevedo, Julián Severiano Prieto Ortiz, Flavio Augusto Artificial vision facial recognized shape descriptors Descriptores de forma reconocimiento facial Visión artificial This article presents the results of analyzing the behavior of the Cone Curvature shapedescriptor (CC) in the task of recognition of facial expressions in 3D images. The CCdescriptor is a representation of the 3D model computed from a set of waves modelingfor each vertex of a polygon mesh. The 3D Facial Expression Database (BU-3DFE) wasused, which contains images with six facial expressions. With the use of the CC descriptor,the expressions were recognized in an average percentage of 76.67% with a neuralnetwork, and of 78.88% with a Bayesian classifier. By combining the CC descriptor withother descriptors such as DESIRE and Spherical Spin Image, it was achieved an averagepercentage of gesture recognition of 90.27%and 97.2 %, using the mentioned classifiers. Se presenta el resultado de analizar el comportamiento del descriptor de forma Cone Curvature (CC) en la tarea de reconocimiento de expresiones faciales en imágenes 3D. El descriptor CC es una representación del modelo 3D que se calcula a partir de un conjunto de ondas de modelado para cada vértice de una malla poligonal. Se empleó la base de datos de rostros 3D (BU-3DFE), la cual contiene imágenes con 6 expresiones faciales. Con el uso del descriptor CC, las expresiones fueron reconocidas en un porcentaje promedio del 76.67% con una red neuronal, y del 78.88% con un clasificador bayesiano. Al realizar una combinación del descriptor CC con otros descriptores como DESIRE y Spherical Spin Image, se logr´o un porcentaje promedio de reconocimiento de gestos del 90.27% y del 97.2 %, usando los mismos clasificadores mencionados previamente. 2015-08-31 2019-09-19T21:38:59Z 2019-09-19T21:38:59Z info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Article Artículo https://revistas.udistrital.edu.co/index.php/reving/article/view/8620 10.14483/23448393.8620 http://hdl.handle.net/11349/19835 spa https://revistas.udistrital.edu.co/index.php/reving/article/view/8620/11129 https://revistas.udistrital.edu.co/index.php/reving/article/view/8620/11296 Copyright (c) 2015 Ingeniería application/pdf text/html Universidad Distrital Francisco José de Caldas Ingeniería; Vol 20 No 2 (2015): July - December; 271-285 Ingeniería; Vol. 20 Núm. 2 (2015): Julio - Diciembre; 271-285 2344-8393 0121-750X
institution Universidad Distrital Francisco José de Caldas
collection DSpace
language Español (Spanish)
topic Artificial vision
facial recognized
shape descriptors
Descriptores de forma
reconocimiento facial
Visión artificial
spellingShingle Artificial vision
facial recognized
shape descriptors
Descriptores de forma
reconocimiento facial
Visión artificial
Rodriguez Acevedo, Julián Severiano
Prieto Ortiz, Flavio Augusto
Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks
description This article presents the results of analyzing the behavior of the Cone Curvature shapedescriptor (CC) in the task of recognition of facial expressions in 3D images. The CCdescriptor is a representation of the 3D model computed from a set of waves modelingfor each vertex of a polygon mesh. The 3D Facial Expression Database (BU-3DFE) wasused, which contains images with six facial expressions. With the use of the CC descriptor,the expressions were recognized in an average percentage of 76.67% with a neuralnetwork, and of 78.88% with a Bayesian classifier. By combining the CC descriptor withother descriptors such as DESIRE and Spherical Spin Image, it was achieved an averagepercentage of gesture recognition of 90.27%and 97.2 %, using the mentioned classifiers.
format Artículo (Article)
author Rodriguez Acevedo, Julián Severiano
Prieto Ortiz, Flavio Augusto
author_facet Rodriguez Acevedo, Julián Severiano
Prieto Ortiz, Flavio Augusto
author_sort Rodriguez Acevedo, Julián Severiano
title Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks
title_short Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks
title_full Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks
title_fullStr Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks
title_full_unstemmed Analysis and Comparison of the Cone Curvature Descriptor in Facial Gesture Recognition Tasks
title_sort analysis and comparison of the cone curvature descriptor in facial gesture recognition tasks
publisher Universidad Distrital Francisco José de Caldas
publishDate 2015
url http://hdl.handle.net/11349/19835
_version_ 1712443810394406912
score 12,131701