English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Previous generations of face recognition algorithms differ in accuracy forimages of different races (race bias). Here, we present the possible underlyingfactors (data-driven and scenario modeling) and methodological considerationsfor assessing race bias in algorithms. We discuss data driven factors (e.g.,image quality, image population statistics, and algorithm architecture), andscenario modeling factors that consider the role of the "user" of the algorithm(e.g., threshold decisions and demographic constraints). To illustrate howthese issues apply, we present data from four face recognition algorithms (aprevious-generation algorithm and three deep convolutional neural networks,DCNNs) for East Asian and Caucasian faces. First, dataset difficulty affectedboth overall recognition accuracy and race bias, such that race bias increasedwith item difficulty. Second, for all four algorithms, the degree of biasvaried depending on the identification decision threshold. To achieve equalfalse accept rates (FARs), East Asian faces required higher identificationthresholds than Caucasian faces, for all algorithms. Third, demographicconstraints on the formulation of the distributions used in the test, impactedestimates of algorithm accuracy. We conclude that race bias needs to bemeasured for individual applications and we provide a checklist for measuringthis bias in face recognition algorithms.

Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?