基于感兴趣区域的微表情识别算法研究  

Research on micro-expression recognition algorithm based on Regions of Interest

作　　者：朱昊 江建[1] ZHU Hao;JIANG Jian(Hunan University of Arts and Science,Changde,Hunan 415000,China)

机构地区：[1]湖南文理学院,湖南常德415000

出　　处：《计算机应用文摘》2024年第1期111-113,共3页Chinese Journal of Computer Application

基　　金：2023年湖南省大学生创新创业项目:基于感兴趣区域(rois)的微表情识别算法研究(S202310549032)。

摘　　要：作为人们内在情绪的流露和掩饰,微表情具有不可伪造和抑制的特点,对评价和了解个体的情感状态具有重要意义。然而,现有的微表情识别方法存在特征表征的主观性和不稳定性等问题,以及数据量不足和微表情类型分布不均的挑战。为解决这些问题,本文提出了一种基于感兴趣区城(ROIs)的微表情识别算法。研究结果表明,该算法在微表情检测和类型识别方面具有较好的性能和先进性,对微表情识别领域的发展具有重要的参考意义和借鉴价值,未来有望在情感识别、心理诊断和虚拟现实等领城得到广泛应用。As the expression and concealment of People's inner emotions,micro-expressions have the characteristics of being unforgettable and suppressed,which is of great significance for evaluating and understanding an individual's emotional state.However,existing methods for micro-expression recognition face challenges such as subjectivity and instability in feature representation,as well as insufficient data volume and uneven distribution of micro-expression types.To address these issues,this paper proposes a micro expression recognition algorithm based on Regions of Interest(ROIs).The research results show that the algorithm has good performance and progressiveness in micro-expression detection and type recognition,and has important reference significance and reference value for the development of micro-expression recognition field.It is expected to be widely used in emotion recognition,psychological diagnosis,virtual realty and other fields in the future.

关 键 词：微表情识别技术 算法研究 感兴趣区域 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]