PSYCH OpenIR  > 认知与发展心理学研究室
基于稀疏张量的微表情识别研究
Project Number61379095
王甦菁
Subtype面上项目
Project Source国家自然科学基金
Project Level国家级项目
2014
End Date2017-12-31
Abstract微表情是一种快速泄露的表情,其特点:持续时间短,变化幅度小。它在自动谎言识别等众多领域都有巨大的应用价值。本项目综合使用计算机视觉技术与认知心理学实验方法,研究微表情自动识别算法及模型。使用点分布模型,研究微表情的自动检测,并构建用于微表情自动识别的数据库。研究彩色空间,用彩色线索进一步提高微表情识别率。针对微表情的特点,研究微表情的稀疏表示,并结合张量分析来保持其空间结构信息。抛开目前张量分析中对张量的所有模(mode)都采取统一变换的方法,根据张量每一模分别表示彩色微表情视频数据的实际意义(即人脸图像信息,彩色空间信息和时间信息),采取不同的变换策略,实现对多类型信息张量的特征抽取新方法。项目完成后,在微表情识别自动领域取得理论和关键技术的突破,提高微表情自动识别的效率和准确性。
Other AbstractMicro-expression is a fast leaked facial expression which is characterized by its short duration and low intensity. It can be effectively applied in lie detection as well as many other fields of studies. The project employs computer vision techniques and research methods from cognitive psychology to develop micro-expression automatic recognition algorithms and models. Employing point distribution model to automatically detect micro-expression; constructing a database for the micro-expression recognition. Analyzing the color space and utilize color information to further increase the accuracy of the micro-expression recognition. To address the characteristic of micro-expression, we investigate the sparse representation of micro-expressions and represent micro-expressions as tensors to preserve its temporal spatial information. The project proposes to perform a different transformation algorithm for each mode of the tensor according to the real meaning of the data in each mode (i.e. a mode may represent a facial image, color space, or temporal data). After the project is completed, through acquiring theoretical and critical technological breakthrough in the field of automated micro-expression recognition; increasing the efficiency and accuracy of automated micro-expression recognition.
Project Funding73
URL查看原文
Project Intro.微表情是以持续时间短,低强度为特征的面部表情。与其他欺骗线索相比,微表情显示出巨大的潜力,是一种很有潜力的欺骗检测线索。首先,我们构建了三个微表情数据库CASME,CASME II和CAS(ME)2。这些数据库可以为自动人脸识别系统的开发提供更多具有较高生态效度的的表情样本。我们研究了彩色空间模型,提出了一种新颖的彩色模型,张量独立彩色空间(TICS),提高了微表情识别的性能。提出了稀疏张量典型相关性分析(STCCA)的微表情特征。提出了一种简单而有效的基于主方向光流的微表情检测和识别的算法。研究了基于光流的微表情主方向最大差分析。提出了一种基于新时空面部表示的新型框架,用于分析微妙的面部运动的微表情。提出了一种基于积分投影的判别时空局部二值模式,解决了时空局部二值模式(STLBP)在微表情识别中的问题。实验结果表明,我们的工作在微表情识别中取得了很好的效果。 另外,还取得了其他一些重要的成果。
Document Type项目
Identifierhttp://ir.psych.ac.cn/handle/311026/31147
Collection认知与发展心理学研究室
Affiliation中国科学院心理研究所
First Author AffilicationInstitute of Psychology, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
王甦菁.基于稀疏张量的微表情识别研究.2014.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王甦菁]'s Articles
Baidu academic
Similar articles in Baidu academic
[王甦菁]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王甦菁]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.