基于卷积神经网络CNN的情绪识别与调节系统  

Emotion Recognition and Regulation System Based on Convolutional Neural Network CNN

作　　者：张迈 张期 李晶晶 ZHANG Mai;ZHANG Qi;LI Jingjing(Yangzhou University Guangling College,Yangzhou,Jiangsu 225000,China)

机构地区：[1]扬州大学广陵学院,江苏扬州225000

出　　处：《移动信息》2024年第10期240-242,245,共4页Mobile Information

基　　金：人工智能助推情绪调节——图像、语音识别的交互式系统(YJ202324)。

摘　　要：针对当今社会背景下生活、工作及人际交往等多方面产生的负性情绪所造成的身心健康问题,文中设计开发了一款基于卷积神经网络的情绪识别与调节系统。该系统基于OpenCV开源计算机视觉库,采用QT作为图形用户界面开发,以Haar分类器作为人脸检测器。该卷积神经网络模型在数据集上的准确率高达98.2%,实际测试集上达到84.61%。用户通过文本和语音输入,系统结合用户输入及模型识别结果提供解决方案,帮助用户缓解负面情绪和压力,达到减少用户心理问题的发生和保障身体健康的目的。In response to the physical and mental health problems caused by negative emotions in various aspects of life,work,and interpersonal communication in today̓s society,this paper designs and develops an emotion recognition and regulation system based on convolutional neural networks.The system is based on the OpenCV open-source computer vision library,developed using QT as the graphical user interface,and using Haar classifier as the face detector.The accuracy of the convolutional neural network model on the dataset is as high as 98.2%,and on the actual test set it reaches 84.61%.Users input text and voice,and the system combines user input and model recognition results to provide solutions,helping users alleviate negative emotions and stress,achieve the goal of reducing the occurrence of psychological problems and ensuring physical health.

关 键 词：人脸表情识别 卷积神经网络 OPENCV QT 情绪调节 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]