Facial expression recognition from video sequences: temporal and static modeling

Cohen, Ira L.; Sebe, Nicu; Garg, Ashutosh; Chen, Lawrence S.; Huang, Thomas S.

doi:10.1016/s1077-3142(03)00081-x

Cited by 761 publications

(434 citation statements)

References 26 publications

Supporting

Mentioning

419

Contrasting

Unclassified

Order By: Relevance

“…There are many different techniques being currently applied to the problems of automatic facial expression recognition and automatic FACS coding such as: Expert Systems [16], Hidden Markov Models [7], Gabor filters [6,17,18,19,20,21,22,23,24] and Optical Flow Analysis [25]. For an overview of the current techniques see [26].…”

Section: Computer Vision Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Investigating the Dynamics of Facial Expression

Reilly

Ghent

McDonald

2006

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. This paper is concerned with capturing the dynamics of facial expression. The dynamics of facial expression can be described as the intensity and timing of a facial expression and its formation. To achieve this we developed a technique that can accurately classify and differentiate between subtle and similar expressions, involving the lower face. This is achieved by using Local Linear Embedding (LLE) to reduce the dimensionality of the dataset and applying Support Vector Machines (SVMs) to classify expressions. We then extended this technique to estimate the dynamics of facial expression formation in terms of intensity and timing.

show abstract

Section: Computer Vision Approachesmentioning

confidence: 99%

“…Recent research has shown that it is not just the expression itself, but also its dynamics that are important when attempting to decipher its meaning [4,5,6,7,8,9,10]. The dynamics of facial expression can be defined as the intensity of the AUs coupled with the timing of their formation.…”

Section: Introductionmentioning

confidence: 99%

Investigating the Dynamics of Facial Expression

Reilly

Ghent

McDonald

2006

Advances in Visual Computing

View full text Add to dashboard Cite

show abstract

“…Most of researches have been done on dynamic textures [7,8,9,10,11,12,13]. [14] Study showed to accept fine grained diversity in facial expression on the basis of Facial Action Coding System (FACS) and action units (AUs).…”

Section: Introductionmentioning

confidence: 99%

Wavelet-threshold based Bit Intensity Measurement: On Facial Expression Recognition

Ane¹

2016

IJCA

View full text Add to dashboard Cite

The objective of this paper is to examine the threshold concept for facial expression recognition, in facial image which is mostly preferred to represent facial expressions in computer vision applications, including face recognition and expression analysis. The goal of this study, bit intensity measurement with thresholding method is applied on facial image for expression recognition. Each image partitioned into equal regions from which the feature binary attributes are extracted and integrated into a feature vector to be used as a face descriptor. Binary measurement has been done matching with reference and neighbouring pixels. Extracted local binary features are integrated for sorting into thresholding based similarity index according to their wave-threshold coefficient values. For evaluation the proposed descriptors JAFFE dataset, Support Vector Machine, Cross validation, fdlibmex were applied.

show abstract

“…Techniques for automating the analysis of facial expressions [10][11][12] are critical to the realization of more natural and effective human-computer interactions, which can add to existing studies of human emotion and affective computing and enhance applications in a broad range of areas. In a given case, however, a false expression can be interpreted as a true expression because the user may be hiding their genuine emotion.…”

Section: Introductionmentioning

confidence: 99%

Personality Trait and Facial Expression Filter-Based Brain-Computer Interface

Chin

Lee

2013

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

In this paper, we present technical approaches that bridge the gap in the research related to the use of braincomputer interfaces for entertainment and facial expressions. Such facial expressions that reflect an individual's personal traits can be used to better realize artificial facial expressions in a gaming environment based on a brain-computer interface. First, an emotion extraction filter is introduced in order to classify emotions on the basis of the users' brain signals in real time. Next, a personality trait filter is defined to classify extrovert and introvert types, which manifest as five traits: very extrovert, extrovert, medium, introvert and very introvert. In addition, facial expressions derived from expression rates are obtained by an extrovert-introvert fuzzy model through its defuzzification process. Finally, we confirm this validation via an analysis of the variance of the personality trait filter, a k-fold cross validation of the emotion extraction filter, an accuracy analysis, a user study of facial synthesis and a test case game.

show abstract

Facial expression recognition from video sequences: temporal and static modeling

Abstract: The most expressive way humans display emotions is through facial expressions. In

Cited by 761 publications

References 26 publications

Investigating the Dynamics of Facial Expression

Investigating the Dynamics of Facial Expression

Wavelet-threshold based Bit Intensity Measurement: On Facial Expression Recognition

Personality Trait and Facial Expression Filter-Based Brain-Computer Interface

Contact Info

Product

Resources

About