Modeling and Analysis of Facial Expressions Using Optical Flow-Derived Divergence and Curl Templates
Anthwal, Shivangi (Indira Gandhi Delhi Technical University for Women)

Fecha:	2021
Resumen:	Facial expressions (FEs) are integral part of non-verbal paralinguistic communication as they provide cues vital for perceiving one's emotional state. Assessment of emotions through FEs is an active research domain in computer vision due to its potential applications in multifaceted domains. In this work, an approach ispresented wherein FEs are modeled and analyzed with dense optical flow-derived divergence and curl templates that embody the ideal motion pattern of facial features pertaining to the unfolding of an expression on the face. Two types of classification schemes based on multi-class support vectormachine and k-nearest neighbor have been employed for evaluation. The efficacy of the approach has been validated with promising results obtained from a comparative analysis of the proposed approach with the state-of-the-art FE recognition techniques on CK+ and JAFFE datasets and with human cognition and pre-trained Microsoft face application programming interface on KDEF dataset.
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió publicada
Materia:	Facial expression recognition ; Emotion analysis ; Optical flow ; Multi-class support vector classification ; K-nearest neighbour classification ; Human Cognition versus Machine Analysis
Publicado en:	ELCVIA. Electronic letters on computer vision and image analysis, Vol. 20 Núm. 2 (2021) , p. 1-21 (Regular Issue) , ISSN 1577-5097

Adreça original: https://elcvia.cvc.uab.cat/article/view/v20-n2-anthwal
Adreça alternativa: https://raco.cat/index.php/ELCVIA/article/view/v20-n2-anthwal
DOI: 10.5565/rev/elcvia.1275
DOI: 10.5565/rev/elcvia.i2021202

21 p, 1.1 MB

El registro aparece en las colecciones:
Artículos > Artículos publicados > ELCVIA
Artículos > Artículos de investigación