English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Facial Micro-Expressions (MEs) are spontaneous, involuntary facial movementswhen a person experiences an emotion but deliberately or unconsciously attemptsto conceal his or her genuine emotions. Recently, ME recognition has attractedincreasing attention due to its potential applications such as clinicaldiagnosis, business negotiation, interrogations, and security. However, it isexpensive to build large scale ME datasets, mainly due to the difficulty ofinducing spontaneous MEs. This limits the application of deep learningtechniques which require lots of training data. In this paper, we propose asimple, efficient yet robust descriptor called Extended Local Binary Patternson Three Orthogonal Planes (ELBPTOP) for ME recognition. ELBPTOP consists ofthree complementary binary descriptors: LBPTOP and two novel ones RadialDifference LBPTOP (RDLBPTOP) and Angular Difference LBPTOP (ADLBPTOP), whichexplore the local second order information along the radial and angulardirections contained in ME video sequences. ELBPTOP is a novel ME descriptorinspired by unique and subtle facial movements. It is computationally efficientand only marginally increases the cost of computing LBPTOP, yet is extremelyeffective for ME recognition. In addition, by firstly introducing WhitenedPrincipal Component Analysis (WPCA) to ME recognition, we can further obtainmore compact and discriminative feature representations, then achievesignificantly computational savings. Extensive experimental evaluation on threepopular spontaneous ME datasets SMIC, CASME II and SAMM show that our proposedELBPTOP approach significantly outperforms the previous state-of-the-art on allthree single evaluated datasets and achieves promising results oncross-database recognition.Our code will be made available.

Extended Local Binary Patterns for Efficient and Robust Spontaneous Facial Micro-Expression Recognition