A main directional maximal difference analysis for spotting facial movements from long-term videos

A main directional maximal difference analysis for spotting facial movements from long-term videos
复制标题

用于从长期视频中发现面部运动的主方向最大差异分析

DOI:
10.1016/j.neucom.2016.12.034
复制
发表时间:
2017-03
期刊:
影响因子:
6
通讯作者:
Fu Xiaolan
Fu Xiaolan
中科院分区:
计算机科学2区
文献类型:
--
作者:
Wang Su-Jing;Wu Suhang;Qian Xingsheng;Li Jingxiu;Fu Xiaolan

文献摘要

参考文献

被引文献

相似文献

微表情的研究越来越受到人们的关注。在长时间视频中发现微表情非常重要,不仅可以为测谎提供线索,还可以减少收集微表情数据所需的劳动力。然而,在发现微表情方面进展甚微。在本文中,我们提出了一个主方向最大差异(MDMD)分析微表达点。MDMD使用光流特征主方向上的幅度最大差异来发现面部运动,包括微表情。MDMD利用分块结构化的人脸区域,获得更准确的表情运动特征,用于从视频中自动识别微表情和宏表情。该方法涉及到人脸运动的时间和空间位置。在CAS(ME)2数据库中进行的微表达式和宏表达式的测试表明,MDMD算法比现有算法具有更好的鲁棒性.
There is an increasing interests in micro-expression researches. Spotting micro-expressions in long-term videos is very important, not only for providing clues for lie detection, but also for reducing the labor required to collect micro-expression data. However, little progress has been made in spotting micro-expressions. In this paper, we propose a Main Directional Maximal Difference (MDMD) Analysis for micro-expression spotting. MDMD uses the magnitude maximal difference in the main direction of optical flow features to spot facial movements, including micro-expressions. Using block structured facial regions, MDMD obtains more accurate features of movement of expressions for automatically spotting micro-expressions and macro-expressions from videos. This method involves both the temporal and spatial locations of face movements. Evaluations using the CAS(ME)2database containing micro-expressions and macro-expressions show that MDMD is more robust than some state-of-the-art algorithms.
DOI: 10.4135/9781483381411.n178
发表时间: 2015
期刊: --
影响因子: --
作者:
E. Prince;Katherine B. Martin;D. Messinger
通讯作者: E. Prince;Katherine B. Martin;D. Messinger
处理感受:特质述情障碍对情绪调节策略和认知情绪处理的表征。
DOI: 10.1371/journal.pone.0005751
发表时间: 2009-06-03
期刊: PloS one
影响因子: 3.7
作者:
Swart M;Kortekaas R;Aleman A
通讯作者: Aleman A
DOI: 10.1007/978-3-642-15567-3_34
发表时间: 2010-09
期刊: --
影响因子: --
作者:
N. Michael;Mark Dilsizian;Dimitris N. Metaxas;J. Burgoon
通讯作者: N. Michael;Mark Dilsizian;Dimitris N. Metaxas;J. Burgoon
DOI: --
发表时间: 1985
期刊: --
影响因子: --
作者:
P. Ekman
通讯作者: P. Ekman
DOI: 10.1006/cviu.1996.0006
发表时间: 1996-01-01
影响因子: 4.5
作者:
Black, MJ;Anandan, P
通讯作者: Anandan, P