Feature-based detection of facial landmarks from neutral and expressive facial images

被引：35

作者：

Gizatdinova, Y ^{[1
]}

Surakka, V

机构：

[1] Tampere Univ, Res Grp Emot Social & Comp, Tampere Unit Comp Human Interact, Dept Comp Sci, FIN-33014 Tampere, Finland

[2] Tampere Univ Hosp, Dept Clin Neurophysiol, FIN-33521 Tampere, Finland

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2006年 / 28卷 / 01期

关键词：

computing methodologies; image processing and computer vision; segmentation; edge and feature detection;

D O I：

10.1109/TPAMI.2006.10

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Feature-based method for detecting landmarks from facial images was designed. The method was based on extracting oriented edges and constructing edge maps at two resolution levels. Edge regions with characteristic edge pattern formed landmark candidates. The method ensured invariance to expressions while detecting eyes. Nose and mouth detection was deteriorated by happiness and disgust.

引用

页码：135 / 139

页数：5

共 20 条

[1]

[Anonymous], 1989, Handbook of social psychophysiology

[2] Classifying facial actions [J].