Review on the effects of age, gender, and race demographics on automatic face recognition

Abdurrahim, Salem Hamed; Samad, Salina Abdul; Huddin, Aqilah Baseri

doi:10.1007/s00371-017-1428-z

Cited by 60 publications

(25 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Despite our use of professional‐grade lighting equipment, Black children were more likely to be missing some FaceReader data. This finding is consistent with other reports of automated facial detection analysis (see Abdurrahim, Samad & Huddin, 2018). 3…”

Section: Resultssupporting

confidence: 94%

Sleep restriction alters children’s positive emotional responses, but effects are moderated by anxiety

Alfano

Bower

Harvey

et al. 2020

Child Psychology Psychiatry

View full text Add to dashboard Cite

Background: An abundance of cross-sectional research links inadequate sleep with poor emotional health, but experimental studies in children are rare. Further, the impact of sleep loss is not uniform across individuals and preexisting anxiety might potentiate the effects of poor sleep on children's emotional functioning. Methods: A sample of 53 children (7-11 years, M = 9.0; 56% female) completed multimodal, assessments in the laboratory when rested and after two nights of sleep restriction (7 and 6 hr in bed, respectively). Sleep was monitored with polysomnography and actigraphy. Subjective reports of affect and arousal, psychophysiological reactivity and regulation, and objective emotional expression were examined during two emotional processing tasks, including one where children were asked to suppress their emotional responses. Results: After sleep restriction, deleterious alterations were observed in children's affect, emotional arousal, facial expressions, and emotion regulation. These effects were primarily detected in response to positive emotional stimuli. The presence of anxiety symptoms moderated most alterations in emotional processing observed after sleep restriction. Conclusions: Results suggest inadequate sleep preferentially impacts positive compared to negative emotion in prepubertal children and that pre-existing anxiety symptoms amplify these effects. Implications for children's everyday socioemotional lives and long-term affective risk are highlighted.

show abstract

Section: Resultssupporting

confidence: 94%

Sleep restriction alters children’s positive emotional responses, but effects are moderated by anxiety

Alfano

Bower

Harvey

et al. 2020

Child Psychology Psychiatry

View full text Add to dashboard Cite

show abstract

“…Ethnicity is a salient example, with findings indicating variability in face recognition algorithms for faces of different ethnicities (O'Toole et al, 2012), with studies demonstrating poorer performance on different demographic cohorts (Klare et al, 2012). This issue has received significant attention in computer vision (Abdurrahim et al, 2018;Garcia et al, 2019), and is an active area of research (Wang & Deng, 2020). While face recognition networks are comprised of multiple steps, the algorithms that find and place landmarks may be a generator of these biases.…”

Section: Study Two -Testing For Potential Biases In Automatic Landmarmentioning

confidence: 99%

Facial metrics generated from manually and automatically placed image landmarks are highly correlated

Jones

Schild

Jones

2021

Evolution and Human Behavior

View full text Add to dashboard Cite

Research on social judgments of faces often investigates relationships between measures of face shape taken from images (facial metrics), and either perceptual ratings of the faces on various traits (e.g., attractiveness) or characteristics of the photographed individual (e.g., their health). A barrier to carrying out this research using large numbers of face images is the time it takes to manually position the landmarks from which these facial metrics are derived. Although research in face recognition has led to the development of algorithms that can automatically position landmarks on face images, the utility of such methods for deriving facial metrics commonly used in research on social judgments of faces has not yet been established. Thus, across two studies, we investigated the correlations between four facial metrics commonly used in social perception research (sexual dimorphism, distinctiveness, bilateral asymmetry, and facial width to height ratio) when measured from manually and automatically placed landmarks. In the first study, in two independent sets of open access face images, we found that facial metrics derived from manually and automatically placed landmarks were typically highly correlated, in both raw and Procrustes-fitted representations. In study two, we investigated the potential for automatic landmark placement to differ between White and East Asian faces. We found that two metrics, facial width to height ratio and sexual dimorphism, were better approximated by automatic landmarks in East Asian faces. However, this difference was small, and easily corrected with outlier detection. These data validate the use of automatically placed landmarks for calculating facial metrics to use in VALIDATING AUTOMATIC FACIAL LANDMARKS 3 research on social judgments of faces, but we urge caution in their use. We also provide a tutorial for the automatic placement of landmarks on face images.

show abstract

“…With this problem definition in terms of users' matching behaviour, the biometric menagerie implies that there are 'inherent differences in the "recognisability" of different users' (Jain et al 2011, p. 22). An increasing number of studies thus locate the potential causes of differential recognizability of users in their 'demographic' characteristics (see Abdurrahim et al 2017). In a recent article, two biometric experts examine how what they term 'certain intrinsic properties of the subject, such as their ethnicity, gender and eye colour' (Howard and Etter 2013, p. 627) influence the distribution of errors in iris recognition systems.…”

Section: Identifying and Classifying 'Problem User Groups'mentioning

confidence: 99%

Securing Identities: Biometric Technologies and the Enactment of Human Bodily Differences

Kloppenburg

Ploeg

2018

Science as Culture

View full text Add to dashboard Cite

Worldwide, biometrics are quickly becoming the preferred solution to a wide range of problems involving identity checking. Biometrics are claimed to provide more secure identification and verification, because 'the body does not lie.' Yet, every biometric check consists of a process with many intermediate steps, introducing contingency and choice on many levels. In addition, there are underlying normative assumptions regarding human bodies that affect the functioning of biometric systems in highly problematic ways. In recent social science studies, the failures of biometric systems have been interpreted as gendered and racialized biases. A more nuanced understanding of how biometrics and bodily differences intersect draws attention to how bodily differences are produced, used, and problematized during the research and design phases of biometric systems, as well as in their use. In technical engineering research, issues of biometrics' performance and human differences are already transformed into R&D challenges in variously more and less problematic ways. In daily practices of border control, system operators engage in workarounds to make the technology work well with a wide range of users. This shows that claims about 'inherent whiteness' of biometrics should be adjusted: relationships between biometric technologies, gender and ethnicity are emergent, multiple and complex. Moreover, from the viewpoint of theorizing gender and ethnicity, biometrics' difficulties in correctly recognising pre-defined categories of gender or ethnicity may be less significant than its involvement in producing and enacting (new) gender and ethnic classifications and identities.

show abstract

Review on the effects of age, gender, and race demographics on automatic face recognition

Cited by 60 publications

References 56 publications

Sleep restriction alters children’s positive emotional responses, but effects are moderated by anxiety

Sleep restriction alters children’s positive emotional responses, but effects are moderated by anxiety

Facial metrics generated from manually and automatically placed image landmarks are highly correlated

Securing Identities: Biometric Technologies and the Enactment of Human Bodily Differences

Contact Info

Product

Resources

About