Can we estimate the perceived comfort of virtual human faces using visual cues?

The sense of strangeness (or discomfort) perceived in certain virtual characters, discussed in Uncanny Valey (UV) theory, can be a key factor in our perceptual and cognitive discrimination. Understanding how this strangeness happens is essential to avoid it in the process of modeling virtual humans. In this paper, we investigate the relationship between images features and the discomfort that human beings can perceive. We extract image features based on Hu Moments (Hum) and Histogram Oriented Gradient (Hog). The saliency detection is also extracted in the specific parts of the virtual face. Finally, a model using Support Vector Machine (SVM) to provide binary classification is suggested. The results indicate accuracy of around 80% in the image estimation process comparing with subjective classification. As a contribution, some areas may benefit from this study for avoiding the creation of characters that may cause strangeness, such as the games, conversational agents and cinema industry.

[1]  James A. Ferwerda,et al.  Applied perception , 2001, IEEE Computer Graphics and Applications.

[2]  Andrew Olney,et al.  Upending the Uncanny Valley , 2005, AAAI.

[3]  Azeddine Beghdadi,et al.  A survey of perceptual image processing methods , 2013, Signal Process. Image Commun..

[4]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  K. MacDorman,et al.  Reducing consistency in human realism increases the uncanny valley effect; increasing category uncertainty does not , 2016, Cognition.

[6]  Lu Zhang,et al.  Contrast and Visual Saliency Similarity-Induced Index for Assessing Image Quality , 2018, IEEE Access.

[7]  Soraia Raupp Musse,et al.  Evaluation of the Uncanny Valley in CG Characters , 2012, IVA.

[8]  Mark Grimshaw,et al.  Facial expression of emotion and perception of the Uncanny Valley in virtual characters , 2011, Comput. Hum. Behav..

[9]  Moncef Gabbouj,et al.  Improving image quality assessment with modeling visual attention , 2010, 2010 2nd European Workshop on Visual Information Processing (EUVIP).

[10]  Susan Persky,et al.  The Independent and Interactive Effects of Embodied-Agent Appearance and Behavior on Self-Report, Cognitive, and Behavioral Markers of Copresence in Immersive Virtual Environments , 2005, Presence: Teleoperators & Virtual Environments.

[11]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Hans-Jürgen Zepernick,et al.  No-reference image and video quality assessment: a classification and review of recent approaches , 2014, EURASIP Journal on Image and Video Processing.

[13]  Daniel Sánchez,et al.  Modelling subjectivity in visual perception of orientation for image retrieval , 2003, Inf. Process. Manag..

[14]  Kaoru Hirota,et al.  A Hu moment invariant as a shape circularity measure , 2010, Pattern Recognit..

[15]  Mitsuru Ishizuka,et al.  Using human physiology to evaluate subtle expressivity of a virtual quizmaster in a mathematical game , 2005, Int. J. Hum. Comput. Stud..