Authentic facial expression analysis

By Nicu Sebe, Michael S. Lew, Yafei Sun, Ira Cohen, Theo Gevers, Thomas S. Huang. Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings., 2004

371 citations recorded by the source corpus.

It is argued that for the computer to be able to interact with humans, it needs to havve the communication skills o humans. One of these skills is the ability to understand the emotional state of the person. The most expressive way humans display emotions is through facial expressions. In most facial expression systems and databases, the emotion data was collected by asking the subjects to perform a series of facial expressions. However, these directed or deliberate facial action tasks typically differ in appearance and timing from the authentic facial expressions induced through events in the normal environment of the subject. In this paper, we present our effort in creating an authentic facial expression database based on spontaneous emotions derived from the environment. Furthermore, we test and compare a wide range of classifiers from the machine learning literature that can be used for facial expression classification.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/21ec41a6ee3c655cf54c6db659d56480fc76e742

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

Citations in the corpus

The MUG facial expression database (2010, background): “Twenty eight subjects participated but the database is not publicly available.”
Theory of Mind and Empathic Explanations of Machiavellianism (2013, background): “For example, to what extent does emotional resonance depend on distinguishing between normal courtesies and pleasantries conveyed in social interactions and specific affective responses contingent on reactions to the qualities of a product/service offering or to what a customer boundary spanner says”
DECAF: MEG-Based Multimodal Database for Decoding Affective Physiological Responses (2015, methodology): “Approaches to predict affect from multimedia can be categorized as (i) content-centric [10], [32], using primitive audio-visual features which cannot adequately characterize the emotion perceived by the viewer, or (ii) user-centric, employing facial expressions [28] and speech intonations [26], whic”
Face Expression Recognition and Analysis: The State of the Art (2012, methodology): “While doing so, they have reported that eliciting sadness and fear in the subjects was difficult [21].”
Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications (2016, methodology): “Many methods focus on recognizing a limited set of primary emotions (usually 6) [115], [116], [123], [130], [137],”
A 3D facial expression database for facial behavior research (2006, background): “Cohn-Kanade [19], JAFFE [21], MMI [8], RU-FACS-1 [9], Ekman-Hager [16,10] USC-IMSC [23], UT-Dallas [25, 24], UA-UIUC [38], QU [33], PICS[49],.”
Local Binary Patterns and Its Application to Facial Image Analysis: A Survey (2011, positive): “In this paper, we focus our attention on studies purely based on visual information, which use facial motion or facial features [118], [119].”