Action unit detection in 3D facial videos with application in facial expression retrieval and recognition

被引：10

作者：

Danelakis, Antonios ^{[1
]}

Theoharis, Theoharis ^{[1
]}

Pratikakis, Ioannis ^{[2
]}

机构：

[1] Norwegian Univ Sci & Technol, Dept Comp & Informat Sci, N-7034 Trondheim, Norway

[2] Democritus Univ Thrace, Dept Elect & Comp Engn, GR-67100 Xanthi, Greece

来源：

MULTIMEDIA TOOLS AND APPLICATIONS | 2018年 / 77卷 / 19期

关键词：

Dynamic 3D mesh sequence; Action unit detection; Facial expression retrieval; Facial expression recognition; REAL-TIME; SEQUENCES; FUSION;

D O I：

10.1007/s11042-018-5699-9

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This work introduces a new scheme for action unit detection in 3D facial videos. Sets of features that define action unit activation in a robust manner are proposed. These features are computed based on eight detected facial landmarks on each facial mesh that involve angles, areas and distances. Support vector machine classifiers are then trained using the above features in order to perform action unit detection. The proposed AU detection scheme is used in a dynamic 3D facial expression retrieval and recognition pipeline, highlighting the most important AU s, in terms of providing facial expression information, and at the same time, resulting in better performance than state-of-the-art methodologies.

引用

页码：24813 / 24841

页数：29