Abstract
Most automatic expression analysis systems attempt to recognize a conventional set of expressions such as happiness, sadness, anger, surprise and fear, etc. Although this set of expressions is the most typical of the face, it is not the most representative/relevant for what the body expressions tell us. This paper presents a novel and generic approach for the recognition of body expressions using human postures. Our method is based on the notion of neutral motion generated from a given expressive one. In a second time, we estimate a residue function, as the difference between the two associated motions, namely the expressive and the neutral motion. More precisely, this function that is inspired by studies from psychology domain, gives a “neutrality” score of a motion. Using this “neutrality score”, we propose a cost function which enables to synthesis the neutral motion from any input expressive motion. The synthesis of neutral motion process is based on two nested Principal Component Analysis providing a space where moving and selecting realistic human animations become possible. Proposed approach is evaluated on four databases with heterogeneous movements and body expressions and it achieved recognition results for body expression recognition that exceed state of the art.
Highlights
Emotion is a complex phenomenon difficult to formalize
We argue that the quality of the generated neutral motion influences body expression recognition rates
DISCUSSIONS AND CONCLUSION In this paper a novel approach for automatic generic recognition of body expressions through 3D skeleton provided by motion capture data is presented
Summary
Emotion is a complex phenomenon difficult to formalize. Interpretation of an emotion is subjective as two different people can perceive and interpret the same emotion differently [1]. The complexity of an expression increases even more as humans express it through different channels such as facial expressions, speech, postures and movement [4]. Several studies from various domains have shown that body expressions are as powerful as facial expressions [5]. If facial expression recognition was widely studied [6], [7], body expression recognition is still an emerging area. With the growth and easy access of devices that track 3-dimensional body, like the Kinect [8], [9] or accelerometer [10] based motion capture system, different applications will emerge based on body expression recognition. Our assumption is that many applications would benefit from the ability to understand human emotional state in
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
