Facial Expression Recognition Using Active Appearance Model

Hong, Taehwa; Yang-bok, Lee; Kim, Yong-Guk; Kim, Hagbae

doi:10.1007/11760023_11

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robust facial feature tracking fromBourel, Chibelushi, and Low 2000 Figure 3.4 above shows points along the eyebrow examined digitally to create measurements. This connection to the nose was determined to be less effective for the purpose of the current study, as discussed byFigure 3.6.Some complex studies placed a face mesh on the subject during videotaping(Hong, Lee et al 2006) to allow capture of numerous simultaneous muscle movements. Other studies examined multiple points on the face through complex software.…”

mentioning

confidence: 99%

Questions in American Sign Language: A quantitative analysis of raised and lowered eyebrows (The University of Texas at Arlington, 2008)

Weast

2009

SL&L

View full text Add to dashboard Cite

Summary of the dissertationThis dissertation examines the nature of eyebrow movement in American Sign Language (ASL). The research contributes to the literature on nonmanuals through the first quantitative eyebrow analysis, with a unique glimpse into the properties of eyebrow movements. Over 3500 measurements were generated through a new methodology with data signed by six native ASL signers. Statements, yes/no questions, and wh-questions were signed in neutral and emotional states. Results display the impact of emotion on eyebrow movements, and show how ASL uses eyebrow height to distinguish between question types and statements in emotional states, with curricula recommendations. The study also presents evidence of a complex layering in ASL eyebrow functions, where one change in eyebrow height can simultaneously represent syntax, grammatical intonation, and other prosodic intonation. The conclusions show that comparing ASL nonmanuals to pitch in English is inadequate. Instead, ASL nonmanuals are best compared to the layering of pitch functions in tone languages.

show abstract

mentioning

confidence: 99%

Questions in American Sign Language: A quantitative analysis of raised and lowered eyebrows (The University of Texas at Arlington, 2008)

Weast

2009

SL&L

View full text Add to dashboard Cite

show abstract

“…For 3-D facial expression representation, it has been proved experimentally by the authors (Quan et al, 2007a;Quan et al, 2007b) that the SSV is able to encode efficiently different facial expressions. A combination of shape and appearance based representations yields the active appearance model (AAM), which could be classified as another statistical model and has been used for facial expression representation (Hong et al, 2006;Edwards et al, 1998). It models the shape as well as grey levels textures and it is mainly used for 2-D facial images in facial expression representation applications.…”

Section: Facial Expression Representationsmentioning

confidence: 99%