A micro-expression recognition algorithm based on long short-term memory networks and feature fusion

doi:10.13741/j.cnki.11-1879/o4.2021.01.020

您当前的位置：

首页 >

文章列表页 >

A micro-expression recognition algorithm based on long short-term memory networks and feature fusion

更新时间：2025-09-01

- A micro-expression recognition algorithm based on long short-term memory networks and feature fusion
- Vol. 47, Issue 1, Pages: 113-119(2021)
- 作者机构：
  
  1:江苏商贸职业学院电子与信息学院
- 作者简介：
- 基金信息：
- DOI：10.13741/j.cnki.11-1879/o4.2021.01.020
  CLC：
- Published：2021
- 稿件说明：
移动端阅览
A micro-expression recognition algorithm based on long short-term memory networks and feature fusion[J]. 2021, 47(1): 113-119.
DOI：

A micro-expression recognition algorithm based on long short-term memory networks and feature fusion[J]. 2021, 47(1): 113-119. DOI： 10.13741/j.cnki.11-1879/o4.2021.01.020.

摘要

为了提高视频识别领域中微表情识别的准确率

提出了一种基于长短期记忆网络与特征融合的微表情识别算法。提取微表情图像的颜色特征和纹理特征

将所提取的空间特征传入卷积神经网络进行融合。设计了学习时域相关性的长短期记忆网络结构

将融合的特征集传入长短期记忆网络学习微表情的时域特征

将长短期记忆网络接入分类器网络识别出微表情的类标签。在两个公开的微表情识别数据集上完成了验证实验

结果显示算法实现了较好的微表情识别性能

在SMIC数据集和CASMEⅡ数据集上的准确率分别达到64.7%和65.8%.

Abstract

关键词

Keywords

references

Views

308

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on dynamic gesture recognition based on attention mechanism convolutional neural network

A new PCA method to increase recognition rate

Salient object detection method based on edge and multi-scale feature fusion

Classification model of dominant species in desertification grassland based on hyperspectral remote sensing

Brain image registration method based on low-resolution auxiliary features and convolutional neural network

Related Author

施丽红

路玉峰

王增才

刘学忠

占钟鸣

李庆武

余大兵

赵乙新

Related Institution

1:江苏商贸职业学院电商与物流学院

1:山东大学机械工程学院

2:山东大学机械工程学院

3:山东大学机械工程学院

⁰