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

Most studies to date that have examined demographic variations in facerecognition accuracy have analyzed 1-to-1 matching accuracy, using images thatcould be described as "government ID quality". This paper analyzes the accuracyof 1-to-many facial identification across demographic groups, and in thepresence of blur and reduced resolution in the probe image as might occur in"surveillance camera quality" images. Cumulative match characteristic curves(CMC) are not appropriate for comparing propensity for rank-one recognitionerrors across demographics, and so we use three metrics for our analysis: (1)the well-known d' metric between mated and non-mated score distributions, andintroduced in this work, (2) absolute score difference between thresholds inthe high-similarity tail of the non-mated and the low-similarity tail of themated distribution, and (3) distribution of (mated - non-mated rank-one scores)across the set of probe images. We find that demographic variation in 1-to-manyaccuracy does not entirely follow what has been observed in 1-to-1 matchingaccuracy. Also, different from 1-to-1 accuracy, demographic comparison of1-to-many accuracy can be affected by different numbers of identities andimages across demographics. More importantly, we show that increased blur inthe probe image, or reduced resolution of the face in the probe image, cansignificantly increase the false positive identification rate. And we show thatthe demographic variation in these high blur or low resolution conditions ismuch larger for male / female than for African-American / Caucasian. The pointthat 1-to-many accuracy can potentially collapse in the context of processing"surveillance camera quality" probe images against a "government ID quality"gallery is an important one.

Impact of Blur and Resolution on Demographic Disparities in 1-to-Many Facial Identification