Holistic processing for other-race faces in chinese participants occurs for upright but not inverted faces

Abstract

Recent evidence suggests stronger holistic processing for own-race faces may underlie the own-race advantage in face memory. In previous studies Caucasian participants have demonstrated larger holistic processing effects for Caucasian over Asian faces. However, Asian participants have consistently shown similar sized effects for both Asian and Caucasian faces. We investigated two proposed explanations for the holistic processing of other-race faces by Asian participants: (1) greater other-race exposure, (2) a general global processing bias. Holistic processing was tested using the part-whole task. Participants were living in predominantly own-race environments and other-race contact was evaluated. Despite reporting significantly greater contact with own-race than other-race people, Chinese participants displayed strong holistic processing for both Asian and Caucasian upright faces. In addition, Chinese participants showed no evidence of holistic processing for inverted faces arguing against a general global processing bias explanation. Caucasian participants, in line with previous studies, displayed stronger holistic processing for Caucasian than Asian upright faces. For inverted faces there were no race-of-face differences. These results are used to suggest that Asians may make more general use of face-specific mechanisms than Caucasians.

Keywords: face recognition; holistic face processing; inversion effect; other-race effect; part-whole effect.

Figure 1

Example whole-face and isolated part test pairs (A) Caucasian female, (B) Asian female, (C) Caucasian male, and (D) Asian male. Whole foil faces differ from the target by only one feature. In the part condition only the critical feature was shown. A whole-face was always shown in the study phase of each trial.

Figure 2

Asian participants show: (A) significant whole-face advantage in the upright condition for both Asian and Caucasian faces; and (B) no evidence of holistic processing for inverted faces of either race. Error bars are as appropriate for making the within-subjects comparison between whole and part conditions (i.e., ±1 SEM of the whole – part difference scores). ***p ≤ 0.001.

Figure 3

Results for Caucasian participants. (A) For upright faces a significant whole-face advantage was observed for Caucasian faces only. (B). There was no significant part-whole effect for either race-of-face when faces were inverted. Note orientation was varied between subjects for the Caucasian participants. Error bars are as appropriate for making the within-subjects comparison between whole and part conditions (i.e., ±1 SEM of the whole – part difference scores). ***p < 0.001.

Figure 4

Standardized part-whole effect (% correct whole − % correct part)/(% correct whole + % correct part) for (A) upright and (B) inverted own-race and other-race faces. Error bars are ±1 SEM.