Subtle expression recognition using optical strain weighted features

Sze-Teng Liong*, John See, Raphael C. W. Phan, Anh Cat Le Ngo, Yee-Hui Oh, Kok Sheik Wong

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

62 Citations (Scopus)


Optical strain characterizes the relative amount of displacement by a moving object within a time interval. Its ability to compute any small muscular movements on faces can be advantageous to subtle expression research. This paper proposes a novel optical strain weighted feature extraction scheme for subtle facial micro-expression recognition. Motion information is derived from optical strain magnitudes, which is then pooled spatio-temporally to obtain block-wise weights for the spatial image plane. By simple product with the weights, the resulting feature histograms are intuitively scaled to accommodate the importance of block regions. Experiments conducted on two recent spontaneous micro-expression databases–CASMEII and SMIC, demonstrated promising improvement over the baseline results.

Original languageEnglish
Title of host publicationComputer Vision - ACCV 2014 Workshops. ACCV 2014
EditorsC. V. Jawahar, Shiguang Shan
Number of pages14
ISBN (Electronic)9783319166315
ISBN (Print)9783319166308
Publication statusPublished - 2015
Event12th Asian Conference on Computer Vision 2014 - Singapore, Singapore
Duration: 1 Nov 20145 Nov 2014

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference12th Asian Conference on Computer Vision 2014
Abbreviated titleACCV 2014

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)


Dive into the research topics of 'Subtle expression recognition using optical strain weighted features'. Together they form a unique fingerprint.

Cite this