[1]李广鹏,刘波,李坤,等.一种基于机器学习的人脸情绪识别方法研究[J].计算机技术与发展,2019,29(05):27-31.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 006]
　LI Guang-peng,LIU Bo,LI Kun,et al.Research on Face Emotion Recognition Based on Machine Learning[J].,2019,29(05):27-31.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 006]
点击复制

一种基于机器学习的人脸情绪识别方法研究()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年05期
页码:
27-31
栏目:
智能、算法、系统工程
出版日期:
2019-05-10

文章信息/Info

Title:
Research on Face Emotion Recognition Based on Machine Learning
文章编号:
1673-629X(2019)05-0027-05
作者:
李广鹏1; 刘波1; 李坤2; 黄思琦3
1. 国防科技大学 计算机学院,湖南 长沙 410073;2. 国防大学政治学院 教研保障中心信息技术室,上海 201602;3. 大连交通大学 软件学院,辽宁 大连 116000
Author(s):
LI Guang-peng1; LIU Bo1; LI Kun2; HUANG Si-qi3
1. School of Computer,National University of Defense Technology,Changsha 410073,China;2. Information Technology Office of Teaching and Research Security Center,Political College of National Defense University,Shanghai 201602,China;3. School of Software,Dalian Jiaotong University,Dalian 116000,China
关键词:
情绪识别; Explicit Shape Regression; PCA; 支持向量机
Keywords:
facial expression recognition; ESR; PCA; SVM
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 05. 006
摘要:
文中对人脸情绪识别整个过程所使用的算法进行分析和总结,并参考了国内外的人脸情绪识别方面的论文和报告,提出一种传统的基于机器学习的人脸图像情绪识别方法。 文中将重点放在人脸表情核心部位(眼睛、眉毛、鼻子和嘴巴),将这些部位的特征向量作为人脸表情主要特征进行处理。 使用的人脸关键部位特征提取算法是基于回归的 Explicit Shape Regression 算法,该算法在人脸特征部位定位方面取得了很好的效果。 因为 Gabor 小波有很好的仿生效果,可以很好地表达表情的变化,所以文中的特征提取算法使用的是 Gabor 小波。 但是考虑到提取出的特征维数过高,算法复杂,耗时较大,在后期用 PCA 算法进行降维处理,降维之后进行表情分类。
Abstract:
We analyze and summarize the algorithms used in the whole process of face emotion recognition,and propose a traditional face image emotion recognition method based on machine learning by referring to domestic and foreign papers and reports on face emotion recognition. We focus on the core parts of facial expression (eyes,eyebrows,nose and mouth) to deal with the feature vectors of these parts as the main features of facial expression. The Explicit Shape Regression algorithm based on regression is used as the key facial feature extraction algorithm,which has been proved to be very effective in face feature location. Because Gabor wavelet has great bionic effect,it can express the change of expression very well,so the feature extraction algorithm in this paper uses Gabor wavelet. But considering thatthe extracted feature dimension is too high,the algorithm is complex and time-consuming,the PCA algorithm is used to reduce the dimension in the later stage,and then the facial expression is classified after dimensionality reduction.

相似文献/References:

[1]陈宗楠,金家瑞,潘家辉*.基于 Swin Transformer 的四维脑电情绪识别[J].计算机技术与发展,2023,33(12):178.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 025]
　CHEN Zong-nan,JIN Jia-rui,PAN Jia-hui*.Swin Transformer-based 4-D EEG Emotion Recognition[J].,2023,33(05):178.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 025]
[2]罗志鑫,刘知贵,唐荣,等.多尺度KAN卷积与跨模态注意力的视听情绪识别[J].计算机技术与发展,2025,(07):100.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0043]
　LUO Zhi-xin,LIU Zhi-gui,TANG Rong,et al.Multiscale KAN Convolution with Cross-modal Attention for Audiovisual Emotion Recognition[J].,2025,(05):100.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0043]

更新日期/Last Update: 2019-05-10