An efficient multimodal 2D + 3D feature-based approach to automatic facial expression recognition
详细信息 查看全文
- 作者：Huibin Lia ; huibinli@mail.xjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Huaxiong Dingb ; huaxiong.ding@ec-lyon.fr" class="auth_mail" title="E-mail the corresponding author ; Di Huang ; c ; dhuang@buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Yunhong Wangc ; yhwang@buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Xi Zhaod ; zhaoxi1@mail.xjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Jean-Marie Morvane ; f ; morvan@math.univ-lyon1.fr" class="auth_mail" title="E-mail the corresponding author ; Liming Chenb ; liming.chen@ec-lyon.fr" class="auth_mail" title="E-mail the corresponding author
- 关键词：Facial expression recognition ; Local texture descriptor ; Local shape descriptor ; Multimodal fusion
- 刊名：Computer Vision and Image Understanding
- 出版年：2015
- 出版时间：November 2015
- 年：2015
- 卷：140
- 期：Complete
- 页码：83-92
- 全文大小：1559 K
文摘
- •
We propose a feature-based 2D+3D multimodal facial expression recognition method.
- •
It is fully automatic benefit from a large set of automatically detected landmarks.
- •
The complementarities between 2D and 3D features are comprehensively demonstrated.
- •
Our method achieves the best accuracy on the BU–3DFE database so far.
- •
A good generalization ability is shown on the Bosphorus database.