A Simple Geometric-Based Descriptor for Facial Expression Recognition
The identification of facial expressions with human emotions plays a key role in non-verbal human communication and has applications in several areas. In this work, we propose a descriptor based on areas and angles of triangles formed by the landmarks from face images. We test these descriptors for...
Guardado en:
Publicado: |
2017
|
---|---|
Materias: | |
Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815090_v_n_p802_Acevedo http://hdl.handle.net/20.500.12110/paper_97815090_v_n_p802_Acevedo |
Aporte de: |
id |
paper:paper_97815090_v_n_p802_Acevedo |
---|---|
record_format |
dspace |
spelling |
paper:paper_97815090_v_n_p802_Acevedo2023-06-08T16:37:54Z A Simple Geometric-Based Descriptor for Facial Expression Recognition Gesture recognition Nearest neighbor search Random processes Conditional random field Dynamic approaches Facial expression recognition Facial Expressions K-nearest neighbors classifiers Non-verbal human Sets of features Training example Face recognition The identification of facial expressions with human emotions plays a key role in non-verbal human communication and has applications in several areas. In this work, we propose a descriptor based on areas and angles of triangles formed by the landmarks from face images. We test these descriptors for facial expression recognition by means of two different approaches. One is a dynamic approach where recognition is performed by a Conditional Random Field (CRF) classifier. The other approach is an adaptation of the k-Nearest Neighbors classifier called Citation-kNN in which the training examples come in the form of sets of feature vectors. An analysis of the most discriminative landmarks for the CRF approach is presented. We compare both methodologies, analyse their similarities and differences. Comparisons with other state-ofthe- art techniques on the CK+ dataset are shown. Even though both methodologies are different from each other, the descriptor remains robust and precise in the recognition of expressions. © 2017 IEEE. 2017 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815090_v_n_p802_Acevedo http://hdl.handle.net/20.500.12110/paper_97815090_v_n_p802_Acevedo |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
Gesture recognition Nearest neighbor search Random processes Conditional random field Dynamic approaches Facial expression recognition Facial Expressions K-nearest neighbors classifiers Non-verbal human Sets of features Training example Face recognition |
spellingShingle |
Gesture recognition Nearest neighbor search Random processes Conditional random field Dynamic approaches Facial expression recognition Facial Expressions K-nearest neighbors classifiers Non-verbal human Sets of features Training example Face recognition A Simple Geometric-Based Descriptor for Facial Expression Recognition |
topic_facet |
Gesture recognition Nearest neighbor search Random processes Conditional random field Dynamic approaches Facial expression recognition Facial Expressions K-nearest neighbors classifiers Non-verbal human Sets of features Training example Face recognition |
description |
The identification of facial expressions with human emotions plays a key role in non-verbal human communication and has applications in several areas. In this work, we propose a descriptor based on areas and angles of triangles formed by the landmarks from face images. We test these descriptors for facial expression recognition by means of two different approaches. One is a dynamic approach where recognition is performed by a Conditional Random Field (CRF) classifier. The other approach is an adaptation of the k-Nearest Neighbors classifier called Citation-kNN in which the training examples come in the form of sets of feature vectors. An analysis of the most discriminative landmarks for the CRF approach is presented. We compare both methodologies, analyse their similarities and differences. Comparisons with other state-ofthe- art techniques on the CK+ dataset are shown. Even though both methodologies are different from each other, the descriptor remains robust and precise in the recognition of expressions. © 2017 IEEE. |
title |
A Simple Geometric-Based Descriptor for Facial Expression Recognition |
title_short |
A Simple Geometric-Based Descriptor for Facial Expression Recognition |
title_full |
A Simple Geometric-Based Descriptor for Facial Expression Recognition |
title_fullStr |
A Simple Geometric-Based Descriptor for Facial Expression Recognition |
title_full_unstemmed |
A Simple Geometric-Based Descriptor for Facial Expression Recognition |
title_sort |
simple geometric-based descriptor for facial expression recognition |
publishDate |
2017 |
url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815090_v_n_p802_Acevedo http://hdl.handle.net/20.500.12110/paper_97815090_v_n_p802_Acevedo |
_version_ |
1768542481080647680 |