Deakin University
Browse

File(s) under permanent embargo

Subtle expression recognition using optical strain weighted features

conference contribution
posted on 2015-01-01, 00:00 authored by S T Liong, J See, R C W Phan, Anh Cat Le Ngo, Y H Oh, K S Wong
© Springer International Publishing Switzerland 2015. 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.

History

Event

Computer Vision. Asian Conference (2014 : Singapore)

Volume

9009

Series

Lecture Notes in Computer Science

Pagination

644 - 657

Publisher

Springer

Location

Singapore

Place of publication

Cham, Switzerland

Start date

2014-11-01

End date

2014-11-02

ISSN

0302-9743

eISSN

1611-3349

ISBN-13

9783319166308

Language

eng

Publication classification

E1.1 Full written paper - refereed

Copyright notice

2015, Springer International Publishing

Editor/Contributor(s)

C Jawahar, S Shan

Title of proceedings

ACCV 2014: Proceedings of the Workshops from the Asian Conference on Computer Vision

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC