摘要
针对现有面部表情识别方法在精度和实时性上的不足,本文提出一种基于改进MobileNetV3的深度学习模型。通过优化网络结构和损失函数,增强模型对细微表情特征的提取能力。实验的结果表明,改进后的模型在静态图像和视频流中均能实现较高精度表情识别,并支持实时检测。
This paper proposes a deep learning model based on improved MobileNetV3 to address the shortcomings of existing facial expression recognition methods in terms of accuracy and real-time performance.By optimizing the network structure and loss function,the model's ability to extract subtle facial expression features is enhanced.The experimental results show that the improved model can achieve high-precision expression recognition in both static images and video streams,and support real-time detection performance.
作者
路晓亚
楚志凯
LU Xiaoya;CHU Zhikai(School of Information and Electronic Engineering,Shangqiu Institute of technology,Shangqiu,China,476000;School of Computer Engineering,Shangqiu Polytechnic,Shangqiu,China,476000)
出处
《福建电脑》
2025年第8期100-104,共5页
Journal of Fujian Computer
基金
2024年度河南省科技攻关项目“智慧教育评价系统中基于深度学习的表情识别技术研究”(No.242102210111)
商丘工学院科研基金资助。
