Development of a facial‐expression database of Chinese Han, Hui and Tibetan people

Abstract

Recently, cross‐cultural facial‐expression recognition has become a research hotspot, and a standardised facial‐expression material system can significantly help researchers compare and demonstrate the results of other studies. We developed a facial‐expression database of Chinese Han, Hui and Tibetan ethnicities. In this study, six basic human facial expressions (and one neutral expression) were collected from 200 Han, 220 Hui and 210 Tibetan participants who lived in these regions. Four experts on each ethnicity evaluated the facial‐expression images according to the expressions, and only those achieving inter‐rater agreement were retained. Subsequently, 240 raters evaluated these images according to the seven emotions and rated the intensity of the expressions. Consequently, 2980 images were included in the database, including 930 images of Han individuals, 962 images of Hui individuals and 1088 images of Tibetan individuals. In conclusion, the facial‐expression database of Chinese Han, Hui and Tibetan people was representative and reliable with a recognition rate of over 60%, making it well‐suited for cross‐cultural research on emotions.

The left side of the face may be fixated on more often than the right side: visual lateralization in recognizing own- and other-race faces

“…A total of 96 faces were used in Experiment 1: 48 Western facial images were obtained from the Cohn-Kanade Dataset ( Lucey et al., 2010 ), and 48 Chinese facial images were obtained from the “facial-expression database of Chinese Han, Hui and Tibetan people” ( Ma et al., 2020 ). Photoshop® CS6 was used to remove the hair, ears, and other irrelevant factors from these faces, and all the faces were converted to grayscale images with a resolution of 640 × 480 pixels.…”

Effects of Tai Chi and Walking Exercise on Emotional Face Recognition in Elderly People: An ERP Study

“…The selection of faces was balanced by gender and emotional valence, and the response keys were balanced between subjects. The valence and arousal of the face materials were rated, and all negative and neutral stimulus pictures showed significant differences in valence and arousal ( Table 2 and Table 3 ) [ 28 ]. All of the images were edited to a uniform format (10.4 × 8 cm), had the same grayscale and luminance background (8-bit color scale), and were framed in a 350 × 270 pixel area.…”

Self-Reported Emotions and Facial Expressions on Consumer Acceptability: A Study Using Energy Drinks

“…The participants were students of Lincoln University and were of Asian origin. Facial expressions vary with different cultures and ethnicities [46,47]; therefore, ethnic-specific facial expressions data were required to understand the implicit emotions depicted by consumers after tasting energy drinks. The participants provided written consent for any sensory deficiency such as anosmia and ageusia, a tasting and video recording session as per ethical requirements-Human Ethics (approval: 2019-68).…”