Under controlled synthetic degradations, facial recognition false negatives rise steeply with blur and low resolution, and error rates are highest for Black women, while false positives peak at near-baseline image quality.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accuracy and Fairness of Facial Recognition Technology in Low-Quality Police Images: An Experiment With Synthetic Faces
Under controlled synthetic degradations, facial recognition false negatives rise steeply with blur and low resolution, and error rates are highest for Black women, while false positives peak at near-baseline image quality.