Matches in SemOpenAlex for { <https://semopenalex.org/work/W26037324> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W26037324 abstract "In previous research, scientists were able to use transient facial thermal features extracted fromThermal Infra-Red Images (TIRIs) for making binary distinction between the affective states.For example, thermal asymmetries localised in facial TIRIs have been used to distinguishanxiety and deceit. Since affective human-computer interaction would require machines todistinguish between the subtle facial expressions of affective states, computers’ able to makesuch binary distinctions would not suffice a robust human-computer interaction. This work, forthe first time, uses affective-state-specific transient facial thermal features extracted from TIRIsto recognise a much wider range of facial expressions under a much wider range of conditions.Using infrared thermal imaging within the 8-14 μm, a database of 324 discrete, time-sequential,visible-spectrum and thermal facial images was acquired, representing different facialexpressions from 23 participants in different situations. A facial thermal feature extraction andpattern classification approach was developed, refined and tested on various Gaussian mixturemodels constructed using the image database. Attempts were made to classify: neutral andpretended happy and sad faces; multiple positive and negative facial expressions; six(pretended) basic facial expressions; partially covered or occluded faces; and faces with evokedhappiness, sadness, disgust and anger.The cluster-analytic classification in this work began by segmentation and detection ofthermal faces in the acquired TIRIs. The affective-state-specific temperature distributions on thefacial skin surface were realised through the pixel grey-level analysis. Examining the affectivestate-specific temperature variations within the selected regions of interest in the TIRIs led tothe discovery of some significant Facial Thermal Feature Points (FTFPs) along the major facialmuscles. Following a multivariate analysis of the Thermal Intensity values (TIVs) measured atthe FTFPs, the TIRIs were represented along the Principal Components (PCs) of a covariancematrix. The resulting PCs were ranked in the order of their effectiveness in the between-clusterseparation. Only the most effective PCs were retained to construct an optimised eigenspace. Asupervised learning algorithm was invoked for linear subdivision of the optimised eigenspace.The statistical significance levels of the classification results were estimated for validating thediscriminant functions.The main contribution of this research has been to show that: the infrared imaging of facialthermal features within the 8-14 μm bandwidth may be used to observe affective-state-specificthermal variations on the face; the pixel-grey level analysis of TIRIs can help localise FTFPsalong the major facial muscles of the face; cluster-analytic classification of transient thermalfeatures may help distinguish between the facial expressions of affective states in an optimizedeigenspace of input thermal feature vectors. The Gaussian mixture model with one cluster peraffect worked better for some facial expressions than others. This made the influence of theGaussian mixture model structure on the accuracy of the classification results obvious.However, the linear discrimination and confusion patterns observed in this work were consistentwith the ones reported in several earlier studies.This investigation also unveiled some important dimensions of the future research on use offacial thermal features in affective human-computer interaction." @default.
- W26037324 created "2016-06-24" @default.
- W26037324 creator A5023632529 @default.
- W26037324 date "2008-03-01" @default.
- W26037324 modified "2023-09-27" @default.
- W26037324 title "Cluster-analytic classification of facial expressions using infrared measurements of facial thermal features" @default.
- W26037324 hasPublicationYear "2008" @default.
- W26037324 type Work @default.
- W26037324 sameAs 26037324 @default.
- W26037324 citedByCount "3" @default.
- W26037324 countsByYear W260373242016 @default.
- W26037324 crossrefType "dissertation" @default.
- W26037324 hasAuthorship W26037324A5023632529 @default.
- W26037324 hasConcept C118552586 @default.
- W26037324 hasConcept C138885662 @default.
- W26037324 hasConcept C144024400 @default.
- W26037324 hasConcept C153180895 @default.
- W26037324 hasConcept C154945302 @default.
- W26037324 hasConcept C15744967 @default.
- W26037324 hasConcept C195704467 @default.
- W26037324 hasConcept C2776401178 @default.
- W26037324 hasConcept C2777375102 @default.
- W26037324 hasConcept C2779302386 @default.
- W26037324 hasConcept C2779304628 @default.
- W26037324 hasConcept C2779812673 @default.
- W26037324 hasConcept C2780905192 @default.
- W26037324 hasConcept C28490314 @default.
- W26037324 hasConcept C31510193 @default.
- W26037324 hasConcept C31972630 @default.
- W26037324 hasConcept C36289849 @default.
- W26037324 hasConcept C41008148 @default.
- W26037324 hasConcept C41895202 @default.
- W26037324 hasConcept C46312422 @default.
- W26037324 hasConcept C4641261 @default.
- W26037324 hasConcept C54654163 @default.
- W26037324 hasConceptScore W26037324C118552586 @default.
- W26037324 hasConceptScore W26037324C138885662 @default.
- W26037324 hasConceptScore W26037324C144024400 @default.
- W26037324 hasConceptScore W26037324C153180895 @default.
- W26037324 hasConceptScore W26037324C154945302 @default.
- W26037324 hasConceptScore W26037324C15744967 @default.
- W26037324 hasConceptScore W26037324C195704467 @default.
- W26037324 hasConceptScore W26037324C2776401178 @default.
- W26037324 hasConceptScore W26037324C2777375102 @default.
- W26037324 hasConceptScore W26037324C2779302386 @default.
- W26037324 hasConceptScore W26037324C2779304628 @default.
- W26037324 hasConceptScore W26037324C2779812673 @default.
- W26037324 hasConceptScore W26037324C2780905192 @default.
- W26037324 hasConceptScore W26037324C28490314 @default.
- W26037324 hasConceptScore W26037324C31510193 @default.
- W26037324 hasConceptScore W26037324C31972630 @default.
- W26037324 hasConceptScore W26037324C36289849 @default.
- W26037324 hasConceptScore W26037324C41008148 @default.
- W26037324 hasConceptScore W26037324C41895202 @default.
- W26037324 hasConceptScore W26037324C46312422 @default.
- W26037324 hasConceptScore W26037324C4641261 @default.
- W26037324 hasConceptScore W26037324C54654163 @default.
- W26037324 hasLocation W260373241 @default.
- W26037324 hasOpenAccess W26037324 @default.
- W26037324 hasPrimaryLocation W260373241 @default.
- W26037324 hasRelatedWork W1479757024 @default.
- W26037324 hasRelatedWork W1594696480 @default.
- W26037324 hasRelatedWork W187802775 @default.
- W26037324 hasRelatedWork W1991983507 @default.
- W26037324 hasRelatedWork W2007428563 @default.
- W26037324 hasRelatedWork W2011797247 @default.
- W26037324 hasRelatedWork W2025630647 @default.
- W26037324 hasRelatedWork W2056049575 @default.
- W26037324 hasRelatedWork W2073011137 @default.
- W26037324 hasRelatedWork W2124901121 @default.
- W26037324 hasRelatedWork W2133080659 @default.
- W26037324 hasRelatedWork W2154784156 @default.
- W26037324 hasRelatedWork W2155417827 @default.
- W26037324 hasRelatedWork W2963772212 @default.
- W26037324 hasRelatedWork W3004167950 @default.
- W26037324 hasRelatedWork W3102749295 @default.
- W26037324 hasRelatedWork W3199073273 @default.
- W26037324 hasRelatedWork W3205437075 @default.
- W26037324 hasRelatedWork W1755233360 @default.
- W26037324 hasRelatedWork W2731944234 @default.
- W26037324 isParatext "false" @default.
- W26037324 isRetracted "false" @default.
- W26037324 magId "26037324" @default.
- W26037324 workType "dissertation" @default.