Expression Recognition Based on Sparse Selection and PLDA

ZHANG Rui; JIANG Chen-zhi; SU Jian-bo

doi:10.3969/j.issn.0372-2112.2018.07.024

您当前的位置：

首页 >

文章列表页 >

Expression Recognition Based on Sparse Selection and PLDA

更新时间：2025-07-16

- Expression Recognition Based on Sparse Selection and PLDA
- Acta Electronica Sinica Vol. 46, Issue 7, Pages: 1710-1718(2018)
- 作者机构：
  
  上海交通大学自动化系系统控制与信息处理教育部重点实验室,上海,200240
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61533012, No.91748120, No.61521063)
- DOI：10.3969/j.issn.0372-2112.2018.07.024
  CLC： TP391.4
- Published Online：25 July 2018，
  
  Published：2018
- 稿件说明：
移动端阅览
ZHANG Rui, JIANG Chen-zhi, SU Jian-bo. Expression Recognition Based on Sparse Selection and PLDA[J]. Acta Electronica Sinica, 2018, 46(7): 1710-1718.
DOI：

ZHANG Rui, JIANG Chen-zhi, SU Jian-bo. Expression Recognition Based on Sparse Selection and PLDA[J]. Acta Electronica Sinica, 2018, 46(7): 1710-1718. DOI： 10.3969/j.issn.0372-2112.2018.07.024.

摘要

提出一种基于稀疏特征挑选（Sparse selection）和概率线性判别分析（Probabilistic linear discriminant analysis）的表情识别方法SS-PLDA.该方法由两部分构成：第一部分是使用稀疏的方法挑选出人脸与表情相关的区域，构造表情的完备特征集；第二部分是针对构造的表情完备特征集里仍含有一些其他信息，运用概率线性判别分析实现表情特征与干扰信息的分离，学习出一个只含有表情信息的子空间，最后基于该表情子空间进行表情识别分析.通过在CK+和JAFFE这两个数据库上面的实验，证实了基于稀疏特征挑选的方法可以得到识别性能的改善，且先使用特征挑选再对所挑选结果应用概率线性判别分析可以达到更好的提升效果.

Abstract

A facial expression recognition method named SS-PLDA is proposed based on Sparse Feature Selection and Probabilistic Linear Discriminant Analysis.The SS-PLDA method contains two steps:1) pick out the most discriminative regions for facial expressions and use these regions to construct a complete facial features set;2) apply Probabilistic Linear Discriminant Analysis Method to separate the useful expression signals from other disturbance information.Therefore

a subspace which only contains expression information is learnt and the expression recognition task is implemented in this subspace.Experimental results on Cohn-Kanade(CK+) database and JAFFE database show that the complete facial features set can improve the performance

and the proposed method outperform the state-of-art ones.

关键词

Keywords

references

Views

252

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Kernel Neighborhood Preserving Projections for Face Recognition

An IR Strong Clutter Background Suppression Algorithm Based on Sparse Kernel Method

A Simultaneous Facial Motion Tracking and Expression Recognition Algorithm

A Local Discriminative Component Analysis Algorithm for Facial Expression Recognition

Fast Orthogonal Kernel Matching Pursuit Based on Greedier Strategy

Related Author

LIU Zheng-kai

SHEN Dao-yi

YU Neng-hai

PANG Yan-wei

FAN Xiang

CHEN Xiao-si

FANG Yi-qiang

WANG Di

Related Institution

Department of EEIS,University of Science and Technology of China

State Key Laboratory of Pulsed Power Laser Technology, Electronic Engineering Institute

Department of Opto-Electronic, Electronic Engineering Institute

State Key Laboratory of Pulsed Power Laser Technology Electronic Engineering Institute Hefei Anhui China

Department of Opto-Electronic Electronic Engineering Institute Hefei Anhui China

⁰