The discrimination of facial sex in developmental prosopagnosia

Abstract

Developmental prosopagnosia (DP) is a neurodevelopmental condition characterised by difficulties recognising and discriminating faces. It is currently unclear whether the perceptual impairments seen in DP are restricted to identity information, or also affect the perception of other facial characteristics. To address this question, we compared the performance of 17 DPs and matched controls on two sensitive sex categorisation tasks. First, in a morph categorisation task, participants made binary decisions about faces drawn from a morph continuum that blended incrementally an average male face and an average female face. We found that judgement precision was significantly lower in the DPs than in the typical controls. Second, we used a sex discrimination task, where female or male facial identities were blended with an androgynous average face. We manipulated the relative weighting of each facial identity and the androgynous average to create four levels of signal strength. We found that DPs were significantly less sensitive than controls at each level of difficulty. Together, these results suggest that the visual processing difficulties in DP extend beyond the extraction of facial identity and affects the extraction of other facial characteristics. Deficits of facial sex categorisation accord with an apperceptive characterisation of DP.

Figure 1

(a) Morphed stimuli used in the morph categorisation task. One male and female model were morphed along a continuum, ranging from 20% (80% male) to 80% female (20% male) in 10% increments. (b) Stimuli used in the sex discrimination task. Forty models were morphed together to create an androgynous average face. Each model was then morphed with the androgynous face to create four weighted morphs (20%, 30%, 40% and 50% identity/sex signal) along a continuum for each model.

Figure 2

Results from (a) the morph categorisation task and (b) the sex discrimination task. Note: bar height gives the mean, bands give the mean ± 1 SEM; *** denotes p < 0.001, ** denotes p < 0.01.