Fully automatic 3D facial expression recognition using local depth features

Facial expressions form a significant part of our nonverbal communications and understanding them is essential for effective human computer interaction. Due to the diversity of facial geometry and expressions, automatic expression recognition is a challenging task. This paper deals with the problem...

Full description

Bibliographic Details
Main Authors: Xue, Mingliang, Mian, A., Liu, Wan-Quan, Li, Ling
Other Authors: NOT FOUND
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers 2014
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/45568
_version_ 1848757321935618048
author Xue, Mingliang
Mian, A.
Liu, Wan-Quan
Li, Ling
author2 NOT FOUND
author_facet NOT FOUND
Xue, Mingliang
Mian, A.
Liu, Wan-Quan
Li, Ling
author_sort Xue, Mingliang
building Curtin Institutional Repository
collection Online Access
description Facial expressions form a significant part of our nonverbal communications and understanding them is essential for effective human computer interaction. Due to the diversity of facial geometry and expressions, automatic expression recognition is a challenging task. This paper deals with the problem of person-independent facial expression recognition from a single 3D scan. We consider only the 3D shape because facial expressions are mostly encoded in facial geometry deformations rather than textures. Unlike the majority of existing works, our method is fully automatic including the detection of landmarks. We detect the four eye corners and nose tip in real time on the depth image and its gradients using Haar-like features and AdaBoost classifier. From these five points, another 25 heuristic points are defined to extract local depth features for representing facial expressions. The depth features are projected to a lower dimensional linear subspace where feature selection is performed by maximizing their relevance and minimizing their redundancy. The selected features are then used to train a multi-class SVM for the final classification. Experiments on the benchmark BU-3DFE database show that the proposed method outperforms existing automatic techniques, and is comparable even to the approaches using manual landmarks.
first_indexed 2025-11-14T09:26:15Z
format Conference Paper
id curtin-20.500.11937-45568
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:26:15Z
publishDate 2014
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-455682017-09-13T14:26:48Z Fully automatic 3D facial expression recognition using local depth features Xue, Mingliang Mian, A. Liu, Wan-Quan Li, Ling NOT FOUND Three-dimensional displays feature selection learning (artificial intelligence) feature extraction Face recognition Vectors human computer interaction Feature extraction support vector machines face recognition Nose Haar transforms Mouth image classification Facial expressions form a significant part of our nonverbal communications and understanding them is essential for effective human computer interaction. Due to the diversity of facial geometry and expressions, automatic expression recognition is a challenging task. This paper deals with the problem of person-independent facial expression recognition from a single 3D scan. We consider only the 3D shape because facial expressions are mostly encoded in facial geometry deformations rather than textures. Unlike the majority of existing works, our method is fully automatic including the detection of landmarks. We detect the four eye corners and nose tip in real time on the depth image and its gradients using Haar-like features and AdaBoost classifier. From these five points, another 25 heuristic points are defined to extract local depth features for representing facial expressions. The depth features are projected to a lower dimensional linear subspace where feature selection is performed by maximizing their relevance and minimizing their redundancy. The selected features are then used to train a multi-class SVM for the final classification. Experiments on the benchmark BU-3DFE database show that the proposed method outperforms existing automatic techniques, and is comparable even to the approaches using manual landmarks. 2014 Conference Paper http://hdl.handle.net/20.500.11937/45568 10.1109/WACV.2014.6835736 Institute of Electrical and Electronics Engineers restricted
spellingShingle Three-dimensional displays
feature selection
learning (artificial intelligence)
feature extraction
Face recognition
Vectors
human computer interaction
Feature extraction
support vector machines
face recognition
Nose
Haar transforms
Mouth
image classification
Xue, Mingliang
Mian, A.
Liu, Wan-Quan
Li, Ling
Fully automatic 3D facial expression recognition using local depth features
title Fully automatic 3D facial expression recognition using local depth features
title_full Fully automatic 3D facial expression recognition using local depth features
title_fullStr Fully automatic 3D facial expression recognition using local depth features
title_full_unstemmed Fully automatic 3D facial expression recognition using local depth features
title_short Fully automatic 3D facial expression recognition using local depth features
title_sort fully automatic 3d facial expression recognition using local depth features
topic Three-dimensional displays
feature selection
learning (artificial intelligence)
feature extraction
Face recognition
Vectors
human computer interaction
Feature extraction
support vector machines
face recognition
Nose
Haar transforms
Mouth
image classification
url http://hdl.handle.net/20.500.11937/45568