您当前的位置：
首页 >
文章列表页 >
NCA-MobileNet： a lightweight facial expression recognition method
Image Processing | 更新时间：2024-05-15
|

    • NCA-MobileNet： a lightweight facial expression recognition method

    • “人脸识别领域的研究取得了新突破。针对传统人脸面部表情识别方法存在的参数量大、计算资源消耗大和识别精度低的问题，研究者提出了一种基于条件协调注意力机制的轻量化人脸面部表情识别方法。通过缩减MobileNet V3网络层数、增大通道数和使用Mish激活函数，实现了特征提取后的非线性化。同时，引入改进的协调注意力机制，可以捕捉面部表情在空间和通道位置上的详细信息。在公开数据集FERPlus和RAF-DB上的实验结果显示，新方法参数量降低15.91%，准确率分别达到了88.84%和85.90%，相比改进前模型准确率分别提升了0.83%和1.39%。这一研究成果为人脸表情识别领域提供了新的解决方案，并有望在实际应用中发挥重要作用。”
      ”
    • Chinese Journal of Liquid Crystals and Displays   Vol. 39, Issue 4, Pages: 522-531(2024)

    • DOI：10.37188/CJLCD.2023-0153    

      CLC： TP391.4

    • Published：05 April 2024，

      Received：25 April 2023，

      Revised：20 May 2023，

    扫 描 看 全 文

  • ZUO Yihai, BAI Wushang, HE Qiusheng. NCA-MobileNet： a lightweight facial expression recognition method. [J]. Chinese Journal of Liquid Crystals and Displays 39(4):522-531(2024) DOI： 10.37188/CJLCD.2023-0153.

  •  
  •  

0

Views

46

下载量

0

CSCD

Alert me when the article has been cited
提交
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

Mobile-based portrait segmentation network with attention mechanism
Anti-UAV object tracking with enhanced backbone and feature rearrangement
Method of vehicle license plate recognition in haze weather based on deep learning
Semi-supervised spatial spectral local discriminant analysis for hyperspectral image feature extraction

Related Author

ZUO Yi-hai
BAI Wu-shang
HE Qiu-sheng
Peng ZHOU
Jian-min YAO
Zhi-xian LIN
Qun YAN
Tai-liang GUO

Related Institution

Nation & Local United Engineering Laboratory of Flat Panel DisplayTechnology, College of Physics and Information Engineering, Fuzhou University
Jinjiang RichSense Electronic Technology Co., Ltd., Jinjiang
College of Information and Communication Engineering， Harbin Engineering University
School of Electronic Information and Artificial Intelligence， Shaanxi University of Science and Technology， Xi 'an
College of Software， Liaoning Technical University
0