Recognition of Facial Expressions in VR an Experiment of Still Photos Versus Three Dimensional Computer Graphic Images

Joey Relouw (), Marnix S. Gisbergen () and Carlos Pereira Santos ()
Additional contact information
Joey Relouw: Breda University of Applied Sciences
Marnix S. Gisbergen: Breda University of Applied Sciences
Carlos Pereira Santos: Breda University of Applied Sciences

A chapter in Augmented Reality and Virtual Reality, 2021, pp 195-206 from Springer

Abstract: Abstract Modern techniques, such as photogrammetry, allows for capturing humans and convert them into realistic looking three-dimensional digital humans. Scanning human faces through photogrammetry and applying them into realistic virtual environments becomes more affordable and easy to use. However, it is unclear whether people differ in recognizing human expressions from 3D photogrammetry faces compared to those captured through traditional media such as photographs. In this study, we compared recognition of ten facial expressions (irritation, hot anger, sadness, despair, disgust, contempt, happiness, elated joy, panic fear, and anxiety) with two intensity levels taken from computer graphic (CG) scanned faces and photographs of two actors. The results, taken from a hundred participants aged between 18–55 years old, showed no differences in facial expression recognition between traditional photographs and computer graphic images. In addition, in line with previous research, the overall recognition of expressions was relatively low (around 50%). These results suggest that CG scanned faces, without any optimization, can already be used within VR environments without risking a loss of expression recognition. However, the results also advocate developers to invest time and money in optimizing the realism in photogrammetry scanned faces to increase the chance of recognizing the right facial expressions when communicating through human faces in virtual reality.

Keywords: Photogrammetry; Photographs; Expressions; Recognition; Computer graphics (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prochp:978-3-030-68086-2_15

Ordering information: This item can be ordered from
http://www.springer.com/9783030680862

DOI: 10.1007/978-3-030-68086-2_15

Access Statistics for this chapter

More chapters in Progress in IS from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().